atlas qualitative research software

The Sheridan Libraries

• Qualitative Data Analysis Software (nVivo, Atlas.TI, and more)
• Sheridan Libraries

Qualitative Data Analysis Software (QDAS) overview

Choosing qda software, core qdas functions.

• Other QDAS Software
• Qualitative Data Sources

For direct assistance

Contact us , JHU Data Services   for assistance with access to nVivo and ATLAS.ti at the Data Services offices on A level, JHU Eisenhower Library.

Visit our website for more info and our upcoming training workshops !

Qualitative research has benefited from a range of software tools facilitating most qualitative methodological techniques, particularly those involving multimedia digital data. These guides focus on two major QDAS products, nVivo and ATLAS.ti.  Both programs can be found on the workstations at the Data Services computer lab on A-level, Eisenhower Library, and nVivo is available through JHU's SAFE Desktop . This guide also lists other QDA software and linked resources.

Many university libraries have produced comprehensive guides on nVivo, ATLAS.ti, and other QDA software, to which we will provide links with our gratitude

Schmider, Christian. n.d. What Qualitative Data Analysis Software Can and Can’t Do for You – an Intro Video . MERIT Library at the School of Education: School of Education, University of Wisconsin-Madison. Accessed January 7, 2020. https://www.youtube.com/watch?v=tLKfaCiHVic .

• Supported Methods
• Decision Factors
• Compare QDA Software

Qualitative Data Analysis (QDA) Software supports a variety of qualitative techniques and methodologies

Qualitative techniques supported by  QDAS

• Coding and Classifying
• Writing: analysis, description, memos
• Relating: finding and annotating connections, relationships, patterns
• Audio/Visual analysis: marking, clipping, transcribing, annotating
• Text mining: computer-aided discovery in large amounts of unstructured text
• Visualization: diagramming, relationship and network patterns, quantitative summary 

QDAS  supported methodologies

• Ethnography
• Case studies
• Grounded theory/ phenomenology
• Discourse/narrative analysis
• Sociolinguistic analysis
• Collaborative qualitative research
• Text analysis & text mining

Overview of qualitative methods from ATLAS.ti:  https://atlasti.com/qualitative-research-methods/

Decision factors for your research

• Methods to feature facilitation (in disciplinary context): How many features directly support your methodology?
• Interface for collection, analysis, reports: Do features accommodate most phases of your research workflow?
• Visualization and outputs: Does it produce and successfully export needed visualization without extensive modification?
• Cost and access to software: Is it worth the investment cost as well as in learning to use it? Look for education discounts.
• Software Comparisons: Commercial & Free. (George Mason University) Lists of flagship software, free software, and tools for converting codebooks among QDA software.
• QDA Software Comparison Chart (NYU Libraries) Comparison chart of QDA software from NYU Library's LibGuide
• Top 14 Qualitative Data Analysis Software Guide with descriptive summaries of the main QDA software, several with business focus.
• Dueling CAQDAS using ATLAS.ti and NVivo Webinar comparing features and use of ATLAS.ti and NVIvo for qualitative data analysis. Includes live demos.

Basic functions common to most QDA programs, and to NVivo and ATLAS.ti in particular:

• Application of a maintained set of terms and short phrases linked to segments of text or audio/video that can be queried and gathered for comparative analysis. 
• Longer narrative notes attached to text or a/v segments, or to codes
• Quick access to codes and segments that can be brought together in panel views for comparison, advanced Boolean search options, and flexible interlinking of segments, codes, and annotation
• Most QDAS facilitates transcribing audio and video, ideally maintaining the links between transcript and A/V segments. 
• Gathering codes, segments, and annotations facilitates pattern discovery and further description of relationships. Some QDAS support social network analysis techniques and visualization
• A range of reports using queries and filters to assemble data and annotations facilitates analysis and writing results.
• ​ Typically includes code tables, social network graphs, and annotated A/V clips.
• Shared access to data & analysis, facilitating comments and discussion, and tracking contributor actions and changes.
• Next: NVivo >>
• Last Updated: Jul 18, 2024 10:26 AM
• URL: https://guides.library.jhu.edu/QDAS

Jump to navigation

Search form

Intersession hours Jan. 3-11. The Libraries are open daily during intersession. Get more details.

• Qualitative Data Analysis

What is Atlas.ti

ATLAS.ti  is a qualitative research tool that can be used for coding and analyzing transcripts & field notes, building literature reviews, creating network diagrams, and data visualization.

The features of Atlas.ti include but are not limited to:

• Data Level Analysis
• Writing up Analysis
• Data Visualization 
• Collaborate with others
• Coding and Organization
• Transcribe Data
• Import, Analyze, and Export Various Data Formats

Why should you use Atlas.ti

ATLAS.ti allows researchers to collect and consolidate primary data and evaluate their significance using a variety of tools. Since ATLAS.ti accepts a wide variety of data formats, it encourages drawing qualitative analytical connections between many different materials, from video and images to survey data to case study transcripts.

It maintains all related coding, memos, and annotations under the same project bundle. In addition, you can export reports, data visualizations and other analyses, and the full project file in multiple formats.

Accessing Atlas.ti

University of Arizona Faculty, Staff, and students have access to Atlas.ti software at the following locations:

• Main Library
• Albert B. Weaver Science-Engineering Library

The Atlas.ti software can be bought and downloaded through the official website . Students ( undergraduate, graduate, and Doctoral ) can receive a reduced price. The University of Arizona does not have a campus license for students not located at the Tucson Main Campus.

Atlas.ti Tutorials

• Atlas.ti Video Tutorials
• ATLAS.ti Academy Learn how to use ATLAS.ti research tools and features to improve your analysis.
• Manuals and Documents

Additional Atlas.ti Guides

• Text Mining Tools and Methods This guide contains resources for researching with text mining.
• Qualitative Research & Tools Find tutorials about conducting Qualitative research, including resources on methodologies and software.
• << Previous: NVivo
• Last Updated: Sep 5, 2024 3:28 PM
• URL: https://libguides.library.arizona.edu/QAnalysis

QUALitative Research & Tools

• Qualitative Research
• Data Repositories
• Transcription
• Atlas.ti Desktop

Books about Altas.ti

• Atlas.ti Web
• What is Atlas.ti Desktop?
• Access to Atlas.ti Desktop
• Atlas.ti Versions
• Related Guides

ATLAS.ti, by Scientific Software Development, is a long-time popular code-and-retrieve software packages for Qualitative research. It was originally designed for grounded theory analysis , but now is flexible enough to handle many purposes. Atlas.ti is now at version 23 (as in 2024)--there is no Atlas.ti versions 10-21. Updates over the past 5 years have been substantial and have drastically increased usability and competitiveness with other options. Compared with other qualitative software, Atlas.ti tends to have more flexibility with viewing and searching.

FAQ: How do I get access to Qualitative Software?

• One copy of Atlas.ti 22 and Atlas.ti 9 is available in Data & Digital Scholarship Services
• A student license is available for as little as ~$50

There is a cloud-based Web version, which is free with the purchase of a desktop license.

See this page in two guides:

• Qualitative Research & Tools
• Software for Digital Scholarship

45 min Live Webinar

ATLAS.ti in 45 minutes , from ATLAS.ti - Webinar offered multiple times per week. Offered in English, Spanish, and Portuguese.

Atlas.ti 23 Improvements

• Cloud Collaboration
• Visualizations for Code-Co-occurences
• Advanced Auto Coding (AI-powered)
• Various tweaks to the interface

20 Minutes, On Demand

Resources from Scientific Software Development

• Atlas.ti 23 Playlist
• Offered in English, Spanish, and German

Other Video Tutorials

• 41 x 2-15min videos as a companion to her book. 
• Global Overview of ATLAS.ti 9 Windows (Atlas.ti) ~1 hr.
• Atlas.ti Video Blog  by Susanne Friese
• Atlas.ti Tutorial  from U Illinois Library

• << Previous: MAXQDA
• Next: Atlas.ti Web >>
• Last Updated: Aug 30, 2024 3:01 PM
• URL: https://infoguides.gmu.edu/qual

Ask a Librarian | Hours & Directions | Mason Libraries Home

Copyright © George Mason University

Qualitative Data Analysis

• Choosing QDA software
• Free QDA tools
• Transcription tools
• Social media research
• Mixed and multi-method research
• Network Diagrams
• Publishing qualitative data
• Student specialists

General Information

For assistance, please submit a request .  You can also reach us via the chat below, email [email protected] , or join Discord server .

If you've met with us before,                        tell us how we're doing .

Stay in touch by signing up for our Data Services newsletter .

Service Desk and Chat

Bobst Library , 5th floor

Staffed Hours: Fall 2024

Mondays:  12pm - 5pm         Tuesdays:  12pm - 5pm         Wednesdays:  12pm - 5pm         Thursdays:  12pm - 5pm         Fridays:  12pm - 5pm        

Data Services closes for winter break at the end of the day on Friday, Dec. 22, 2023. We will reopen on Wednesday, Jan. 3, 2024.

ATLAS.ti Software Access

ATLAS.ti is a qualitative research tool that can be used for  coding and analyzing transcripts & field notes,  building literature reviews,  creating network diagrams, and  data visualization.

NYU Students are able to access  ATLAS.ti for free via the  the  Virtual Computing Lab  (VCL).

Warning regarding the VCL:  Please be sure you are familiar with successfully saving your when working on the VCL before you begin coding.  We have several incidents of loss to data due to issues in saving materials, therefore it is best for users to export the project bundle if they want a copy on their personal computer. We recommend you access the VCL using Chrome or Firefox, given we have had issues with the Safari browser.

NYU community members can access ATLAS.ti for free on the 5th floor of Bobst Library in the  Data Services Lab .

For Comprehensive information, please see the NYU IT ATLAS.ti page .

Data Services ATLAS.ti Tutorials

• Featured Tutorials
• ATLAS.ti Slides and Data
• Digital Tools for Qualitative Data Analysis A side-by-side overview of software platforms for qualitative data analysis
• Introduction to Atlas.ti Start a QDA project from uploading text, classify and code transcripts, and produce analyses
• Social Media Scraping for Qualitative Research Learn small scale web scraping using Twitter, ATLAS.ti, and MAXQDA.
• Intro to Atlas.ti Google Slides tutorial to Atlas.ti
• ATLAS.ti Practice Dataset 1 2 interview transcripts and 2 photos of New York Chefs.

ATLAS.ti Resources

• Learning Resources
• Working in Teams
• Transfering project
• Working with Audio Files
• ATLAS.ti 9 Handbook The complete PDF handbook describing the features of ATLAS.ti.
• What's new in ATLAS.ti 9? Documentation on the features updated for this version of ATLAS.ti.
• ATLAS.ti 9 Video Tutorials ATLAS.ti curated video tutorials for learning the features of the tool.

Please see Atlas 9 Instructions

The project administrator sets up a  Master project . See  Creating a New Project .

The project administrator  adds documents  to the project and possibly a list of codes.

The project administrator saves the project and exports it. This means creating a  project bundle file  .

All team members  import  the project bundle file and begin their work.

To combine the work of all team members, each team member creates a  project bundle file  and sends it to the project administrator.

The project administrator  merges  all sub projects and creates a new Master file.

Mary exports the new Master file and distributes it to all team members. See  Transfer Projects .

The team members continue their work.

This cycle continues. If new documents need to be added to the project, this needs to be done by the project administrator. A good time for doing this is after merging and before creating the new Master file.

You find step-by-step instructions here:

for project administrators

for team members

Important to Know

If all team members should work on the same documents, it is essential that only the project administrator is setting up the project adding all documents. Otherwise, the documents are duplicated or multiplied during the process of merging. See  Adding Documents.

Team members  must not edit  documents. If they do, the edited documents cannot be merged, and you end up with duplicates. If document editing is necessary, this needs to be done by the project administrator in the Master project!

The location of where ATLAS.ti stores project related data can be determined by each user. See  Working with ATLAS.ti Libraries.

Document libraries CANNOT be shared. Each person always works with her/his own copy of the data set within her/his own environment of ATLAS.ti.

To import your project from Atlas 8 into ATLAS.ti 9,

In ATLAS.ti 8 select Project  Export --> Project Bundle or QDPX Project Bundle. This creates a single-file copy of your project.

In ATLAS.ti 9, select “Import Project” from the start screen.

IMPORTANT: While project transfer from ATLAS.ti 8 Windows to ATLAS.ti 9 is fully supported, backwards compatibility is limited to .QDPX files.

To transfer your project to another computer with either ATLAS.ti 9 installed, simply export it via File --> Export and select either .atlproj or .qdpx project bundles.

Import iTunes Voice Memos as (.M4A) files into Atlas! According to the Atlas software we have installed in Data Services, these are the audio/video file types that Atlas supports: *.AIF, *.AIFC, *.AIFF, *.ASF, *.AU, *.AVI, *.DVR-MS, *.IVF, *.M1V, *.M2V, *.M4A, *.M4B, *.M4V, *.MID, *.MIDI, *.MOV, *.MP2, *.MP2V, *.MP3, *.MP4, *.MP4V, *.MPA, *.MPE, *.MPEG, *.MPG, *.MPV2, *.RMI, *.SND, *.WAV, *.WM, *.WMA, *.WMV

ATLAS.ti 22 Resources

• ATLAS.ti 22 Handbook Instruction manual for the windows version of ATLAS.ti 22
• What's new in ATLAS.ti 22? Documentation on the newly introduced features in ATLAS.ti 22
• ATLAS.ti 22 Video Tutorials ATLAS.ti curated video tutorials for learning the features of the tool.

• << Previous: Taguette
• Next: MAXQDA >>
• Last Updated: Sep 3, 2024 2:34 PM
• URL: https://guides.nyu.edu/QDA

• Langson Library
• Science Library
• Grunigen Medical Library
• Law Library
• Connect From Off-Campus
• Accessibility
• Gateway Study Center

Email this link

Software for data analysis.

• Qualitative Data Analysis Software (Free)
• Python Libraries
• StoryMaps This link opens in a new window
• Other Helpful Tools - StatTransfer and OpenRefine
• DSS Programming Workshops

Online Learning -- Software & Coding

Safari Books Online - brings you ebooks and videos from 200+ respected publishers, including O’Reilly, Pearson, Wiley, Packt, Harvard Business Review, and Wharton Digital Press.

Why Atlas.ti

Atlas.ti   is a  qualitative data analysis  package. Atlas.ti helps researchers to organize and analyze complex textual and multimedia  data . The software allows users to classify, sort and arrange thousands of pieces of information. It also accommodates a wide range of research methods. 

Where To Find It!

Atlas.ti is available by license , with the first month free.  UCI does not license Atlas.ti at this time.

Online Tutorials

• Tutorials from Atlas.ti (English & Spanish)
• Free Demo Webinars from Atlas.ti
• Manuals and Documents from Atlas.ti

• << Previous: Qualitative Data Analysis Software (Paid)
• Next: Dedoose >>
• Last Updated: Aug 13, 2024 9:57 AM
• URL: https://guides.lib.uci.edu/dataanalysis

Off-campus? Please use the Software VPN and choose the group UCIFull to access licensed content. For more information, please Click here

Software VPN is not available for guests, so they may not have access to some content when connecting from off-campus.

MAXQDA vs. ATLAS.ti vs. Delve: What's the Best Qualitative Coding Software?

 Qualitative data analysis (QDA) software is often the tool of choice for qualitative researchers. It's the tool that can truly make a difference in the quality and efficiency of your work. But when it's time to pick the best QDA software for your needs, a few key considerations come into play.

In this article, we'll compare three popular QDA software options: ATLAS.ti, MAXQDA, and Delve. We'll introduce each option, explore their strengths and weaknesses, and help you choose the right tool for your specific qualitative research needs.

But before we jump in, let’s clear up a frequent point of confusion amongst qualitative researchers.

Are QDA Software and Computer-Assisted Qualitative Data Analysis Software (CAQDAS) the Same Thing?

Yes, QDA software and computer-assisted qualitative data analysis (CAQDAS) are terms used to describe the same software. QDA software is also known as CAQDAS, and vice versa.

Both terms describe software that helps researchers organize, code, and analyze data to identify patterns and themes. QDA software is probably used more often because it's a bit easier to say, type, and remember.

As you research ATLAS.ti, MAXQDA, and Delve, you may see either acronym, so we wanted to clarify there is no distinction between the terms. 

How to Choose the Right Qualitative Coding Software

Now, let’s establish some criteria for selecting the best QDA software for your unique research needs. Doing so can streamline your decision-making process and avoid investing time and resources in an unsuitable tool.

Here are four ways to approach your ultimate decision:

Your Budget

Qualitative data analysis software comes in a wide range of price points. Some offer discounts for students and educators, while others do not. There are monthly and annual subscription options and also one-time purchases. Finding a tool that aligns with your budget while meeting your research requirements is essential.

Qualitative analysis is a time-intensive process. If you have tight research deadlines, consider the time it takes to learn and adapt to a new QDA software. Efficiently integrating a new tool into your workflow is crucial to meeting your research objectives.

Identify the specific features that are important for your research. Do you need software capable of handling extensive datasets? Are collaboration tools essential for your research team? Pinpointing your needs will help you find a software solution that simplifies and streamlines your qualitative research.

Your Experience Level

Consider your familiarity with qualitative analysis. If you're new to the field, look for software that is user-friendly and facilitates the discovery of nuanced insights. For experienced researchers, more sophisticated features may be more desirable.

Once you've taken these factors into account, you can start to deduce the QDA software that best aligns with your budget, time constraints, research goals, and experience. 

Comparing ATLAS.ti vs. MAXQDA vs. Delve

Now, let's look at the features and capabilities of ATLAS.ti, MAXQDA, and Delve.

While these QDA software programs share standard functions related to qualitative analysis, they differ significantly in terms of user interfaces, features, pricing structures, supported operating systems, and collaborative capabilities.

ATLAS.ti: A Sophisticated Coding Tool

ATLAS.ti has been a prominent player in the CAQDAS field for over two decades. It is a sophisticated tool with advanced functionality designed to assist researchers in various qualitative research methods. While ATLAS.ti offers an extensive feature set, it may have a steeper learning curve, making it more suitable for experienced researchers.

Key Features:

Functionality: ATLAS.ti provides a wide array of features, making it suitable for in-depth research projects.

Desktop and Web Versions: It offers both desktop and web versions to cater to various user preferences and needs.

Sophisticated Software: The software is robust but complex, sometimes to a fault. It is best for experienced researchers or those with enough time to learn advanced software.

Extensive research endeavors. ATLAS.ti shines with its formidable power and sophistication. It's tailor-made for seasoned researchers who have substantial experience with qualitative analysis. 

Licensing Model

Desktop (device-specific) 

Need to update software

Need upgrades for all features

Web version (limited functionality ⚠️)

Full pricing information for ATLAS.ti .

⚠️ You can use both the desktop and web versions of ATLAS.ti together, but they don’t automatically synchronize. ATLAS.ti Web (the more affordable option) also does not support all ATLAS.ti features. You can’t set up a mixed-team project where some people work in the desktop version and others in the web version.

MAXQDA: Versatile Yet Complex

MAXQDA is recognized for its versatility and ability to support mixed-method research . It offers tools for coding, analyzing, and visualizing qualitative data, catering to researchers across disciplines. However, customers give the company low marks for customer service and overall training resources, lengthening the learning curve. Its pricing may also not align with all budgets.

Versatile: MAXQDA accommodates various qualitative research methods.

Steep Learning Curve: Its comprehensive functionality may require a significant learning curve, exacerbated by poor customer service and learning resources.

Price Point: MAXQDA's pricing may not align with all budgets, especially for students.

MAXQDA shines with its versatility for mixed-method research. It's tailor-made for seasoned researchers well-versed in the nuances of qualitative analysis.

Requires software updates

Needs upgrades to use collaborative features

$232 per year (desktop, device-specific, no collaboration)

$432 per year (MAXQDA TeamCloud subscription)

Full pricing information for MAXQDA .

Delve: Simplifying Qualitative Data Analysis

Delve is a QDA software known for its user-friendliness, collaboration capabilities, and affordability. It caters to a wide range of users, making it an ideal choice for researchers new to qualitative data analysis or those seeking a cost-effective coding solution.

User-Friendly Interface : Delve's interface is intuitive, ensuring a smooth learning curve for users.

Remote Collaboration : As a web-based tool, Delve facilitates seamless collaboration among researchers, regardless of their physical locations.

Effortless Project Sharing : Collaborative research is simplified with Delve's sharing feature, allowing for easy project sharing and role assignment.

Cross-Platform Compatibility : Delve ensures consistent performance across all major operating systems, enhancing flexibility.

Automated Intercoder Reliability : Delve automates intercoder reliability scores, saving time and improving the accuracy of qualitative analysis.

Side-By-Side Coding Comparisons : Researchers can code independently and later compare their coding approaches for better insights.

Responsive Customer Support : Delve's customer support is highly responsive, providing timely assistance when needed.

Qualitative Analysis Learning Center : For those new to qualitative analysis, Delve offers various learning resources and tutorials.

Flexible Academic Pricing : Delve offers budget-friendly options, recognizing the financial constraints faced by students.

Delve caters to a wide range of users, including students, academics, market researchers, analysts, and social science professionals. It is ideal for those new to qualitative data analysis or seeking an efficient, budget-friendly alternative focused on collaborative qualitative analysis .

100% web-based (accessible from any device)

$432 per year (with annual discount)

$50 per month (commercial pricing)

$18 per month or $200 per year (with academic discount)

Full pricing information for Delve .

Here’s a table to show how these QDA software options stack up:

This comparison lets you make an informed decision based on your research needs, experience level, and budget constraints. 

While Delve offers user-friendliness, remote collaboration, and affordability, ATLAS.ti and MAXQDA have their own strengths that cater to specific research contexts. 

Qualitative analysis doesn't have to be overwhelming

Take delve's free online course to learn how to find themes and patterns in your qualitative data. get started here..

User Reviews: ATLAS.ti vs. MAXQDA vs. Delve

Now let’s take a look at what actual users of ATLAS.ti, MAXQDA, and Delve say about each QDA software. To make it easier to compare quickly, we organize these comparisons based on what most researchers consider important when they pick the right option for themselves.

❌ What Customers Say About MAXQDA

“Cost restrictive for students.” Read more. 

“It is rather expensive and I would like to find some software that offers a very low-cost student edition. Our students are not going to be doing as much research as some doc students as they are leaders in public schools. Purchasing an expensive product doesn't make sense.” Read more.

“Because MAXQDA is quite costly, it is a barrier that detracts from more widespread use.” Read more. 

❌ What Customers Say About ATLAS.ti

“Student licenses are valid for only 2 year and will expire. If you are a grad student who expends hundreds of hours on coding and analyzing your data with AtlasIT, you'll find that you are unable to continue to work on your project after you graduate unless you buy a commercial license. The expenses will add up rapidly. Student licenses should not expire and prevent users from continuing to work with their data using their purchased version of the software.” Read more.

✅ What Customers Say About Delve

“Delve is less expensive than other options and easier to use.” Read more.

“Very reasonably priced.” Read more.

“The education pricing is so inexpensive that Delve would be highly appropriate for students just learning how to code as well as seasoned researchers. It's also flexible enough that you only pay for the time that you're using the program - in my case I used it all the time at first, then paused my membership and reopened it when I had new data and analysis to do.” Read more. 

Cloud-based Collaboration

 “A downside of using MaxQDA was that it had to be purchased for each individual laptop (as far as I am aware) and so we were limited to coding on just one device.” Read more.

“The teamwork options are not as seamless as they could be. You have to set up coding in a particular way or merges do not work properly. We find there are not as much functionality as we would like when comparing coding results between different coders.” Read more.

“You cannot have multiple users working on the same project and automatically save. merging projects is not a very obvious function.” Read more.  

“The functionality for teams is CLUNKY! Not easy to work together at all in my opinion.” Read more.

“The gap between Mac and Windows is significant and creates the most issues for users. When training a hybrid course, switching back and forth is tedious and it's always a little awkward when I have to say, "sorry Mac users, this isn't as easy or isn't available..." Read more.

“Delve is very easy to learn and use individually or as a team. Using Delve has shortened our time to process text for coding and organizing for presentations. Used with time codes, it can also shorten video editing times. We've used several other products and found Delve to be a perfect complement to our workflow.” Read more. 

“We were up and running with Delve within minutes. It was very intuitive to use, with very quick setup. We were able to easily collaborate and facilitate our thematic analysis process without a steep learning curve and at a very reasonable price.” Read more. 

“Wonderful user interface and coding process, loved how easy it is to collaborate with others.” Read more.

“Most importantly, Delve makes it easy and intuitive to share my results with my collaborators.” Read more.

“Loved how easy it is to collaborate with others.” Read more.  

“It works easily when collaborating with others on a qualitative project. When coding I like the flexibility of this software to rename, regroup as you conduct your analysis.” Read more. 

Learning Curve

❌  What Customers Say About MAXQDA

“The actual coding process can be unintuitive and has a steep learning curve.” Read more.

“Licensing, different devices and shared projects can get complicated. Also, getting the most out of it does require a rather steep learning curve.” Read more.

“There is a required learning curve for MAX QDA. You will need to commit some time to learning the software to succeed.” Read more. 

“This software requires specific training and a learning curve to assimilate its features and get the most out of it.” Read more.

“Delve has made coding qualitative data so simple and fast. The user-friendliness makes it a must-have for any qualitative researcher.” Read more.  

“Delve was very easy to use and it was quick to pick up. All of the functions I used were user-friendly and perfect for my research project.” Read more. 

“There is no steep learning curve involved. You simply upload or paste your transcripts and start coding.” Read more. 

“For a first-time researcher like me, Delve made the process so simple and effective. It helped me save time that I might've wasted in trying to learn another software that wouldn't be as user-friendly.” Read more.

Customer Support / Tutorials

“I also wish tutorials and professional learning development would be more accessible. [...] It sometimes becomes overwhelming and difficult without guidance.” Read more. 

“The YouTube videos explaining how to use Atlas.ti are TERRIBLE.” Read more.

"Worst customer support I've ever experienced!" Read more.

“Very simple and doesn't require any long training hours. Just go through 30 min long quick short videos and you are all set.” Read more.

“Delve offers a training course and a follow-along training to help beginners who are coding for the first time.” Read more. 

“It has very good tutorials that explain in detail how to use the product. Also, the tutorials are short so you don't have to spend lots of time to understand how the tool works. This aspect was very important for me, as I didn't had lots of time to work with the data.” Read more.  

​​“The customer support is superb! Support from Delve was so responsive, I was extremely pleased with the level of services I received.” Read more.

“One of the things that I like most about this software is that the support team is incredibly responsive and helpful. They answer questions quickly.” Read more.

User Interface

“The user interface of this software leaves a lot to desire.” Read more.

“I found it a bit confusing to use the software to organize the data once all of the data is coded. There are supposedly a ton of functions that allow you to organize the data, yet, even with doing the online, it still felt difficult to me.” Read more.

“While coding, there is an interface on the left that is very restrictive. […] I think the program is confusing, especially during analysis.” Read more. 

“It is difficult to use because of the multiple buttons on its entrance platform. In addition, making interpretations can be complicated if you do not handle it frequently.” Read more.

“The UI is very straightforward and simple to use. Coding text is very easy and tags are automatically compiled into a list for easy access. You can navigate/sort your transcripts by code, meaning it's easy to cross-reference.” Read more.

“The simplicity and the ease in navigating their tool is commendable.” Read more. 

“Delve was easy to use. I used it for my doctoral research and it helped me to organize my interview information into codes and categories.” Read more.  

“Delve's beauty is in it's simplicity and ease of use, yet it is intelligent enough to get the thematic analysis done for you in a very fast space of time, at a much more detailed rate than us mere mortals. Highly recommended, company and the software.” Read more. 

“Great feature set is very intuitive to learn and start using right away. Interface makes it very easy to construct codes, highlight and code text and view excerpts in different ways. Being able to code as little as a word or as much as a paragraph (or multiple paragraphs) results in more robust coding.” Read more.  

Auto-Save Work

“The way it saves your work can be a bit confusing at first and can cause some anxiety about whether it saved properly or not.” Read more.  “We had to upload copies in a way that was confusing and sometimes the work we did was saved to the wrong place.” Read more. 

“Crashes and loses data! After reporting, the problem has not been fixed…” Read more. 

“Since I use the software to analyze my data directly through the website, I don't need worry about losing my progress when my computer breaks down. It happened several times during my dissertation, but the work on Delve was always perfectly saved.” Read more.

Bugs / Research Delays

“I came across glitches sometimes that can be frustrating. Although MAXQDA saves projects automatically, there have been instances of the software freezing or slowing down, even on small datasets.” Read more.

“Web version works too slowly and errors occur when encoding PDF files. There are also problems when exporting projects so that it is not even possible to continue working in the desktop version.” Read more.

“The product is very easy to both access and use. You don't need to download any software, it always saves your work.” Read more. 

“It is easy-to-use, with a clean interface that required no lag-time of reviewing instructions or familiarizing myself with the tool.” Read more.

“Using Delve saves me tremendous amounts of time, and brings my research insights more to life! It saves me loads of time when preparing a report and helps me digest qualitative themes more efficiently.” Read more. 

"Fantastic qualitative analysis and organization tool that saves time!" Read more. 

“It is a well thought out and efficient piece of software well worth using as a student or researcher.” Read more. 

Explore all of the Delve user reviews .

Comparing Delve to ATLAS.ti and MAXQDA

Take a look at how ATLAS.ti, MAXQDA, and Delve rank on user reviews.

ATLAS.ti vs. Delve

Check out the complete ATLAS.ti vs. Delve comparison .

MAXQDA vs. Delve

Check out the complete MAXQDA vs. Delve comparison .

[Compare Delve to other popular QDA software options like Dedoose and NVivo .]

Why Choose Delve?

Designed by researchers, Delve simplifies all facets of the qualitative research process. It offers powerful coding capabilities that usher in a new era of efficiency, granting you more control over your research structure. No more lost notes, no more corrupt files, no more manually merging data. 

Check out these specific features and capabilities that set Delve apart:

Simplicity in Software

Delve sets itself apart with its intuitive interface, eliminating the need for extensive training or the acquisition of specialized jargon. Users can dive right into their research without the steep learning curve associated with other QDA software.

Collaborative Project Sharing

Collaboration is at the core of modern qualitative research, and Delve excels in this area. Using Delve, sharing your projects with fellow researchers for peer-debriefing is hassle-free. Adding or removing users and assigning specific roles can be accomplished with a few clicks, streamlining your teamwork.

Can Edit : Grants full project access for content addition, coding, memos, and inviting others, but requires an active subscription.

Can View : Allows project viewing without editing rights. It's free, and no subscription is needed for viewing.

Memos Made Simple

Analytical memos lead to more effective research. Memos can help. Delve's analytical memo feature lets researchers jot down quick notes during data collection, coding, or analysis. These memos help keep thoughts, ideas, and questions organized, contributing to more nuanced research results.

Reliable Intercoder Scores

Delve simplifies the coding process by automating intercoder reliability scores. This not only saves time but also ensures accuracy and consistency in qualitative analysis. With Delve, you can trust in the efficiency and reliability of your coding process.

Comparing Codes Collaboratively

Delve fosters collaborative coding with side-by-side comparisons of coding decisions on the same transcript. Users can code individually and then compare their work, enhancing teamwork while maintaining independence.

Responsive Customer Support

Delve users commend the exceptional customer service. Whether through email or live chat, the support team responds promptly to questions and challenges. Timely support minimizes delays, ensuring that research proceeds on schedule.

The Learning Hub

Qualitative analysis can be intricate. Delve simplifies the learning process, offering coding tips, YouTube tutorials , an intuitive help center , and insights into qualitative research methods through the Learning Center . This resource equips you with the knowledge you need for any qualitative research project.

Code Descriptions for Clarity

Delve allows researchers to write down thoughts within the code detail page or share them with colleagues. Delve code descriptions provide context, connecting them to the quotes that inspired them. This feature aids in understanding the rationale behind code assignments.

Flexible Account Management

Delve understands the financial constraints faced by students. It offers the flexibility to pause or cancel accounts as needed. This accommodating policy specifically aligns with the realities of student life, providing peace of mind in managing expenses.

Adapting to Remote Research

Remote research is an increasingly common practice in qualitative research. Delve's web-based coding software caters to this nascent trend, offering features that facilitate remote collaboration and adapt to the demands of modern research practices.

Consistency Across Operating Systems

Delve ensures uniform performance on all operating systems, eliminating compatibility concerns. Whether on Windows, macOS, or Linux, Delve offers a seamless transition between devices. No matter where you are or what device you use, you can easily code with Delve. 

Delve: The Simple QDA Software Solution

Delve emerges as an ideal choice for researchers seeking a user-friendly, collaborative, and cost-effective CAQDAS solution. As the ever-evolving landscape of qualitative data analysis changes, Delve stands out as a practical and efficient tool to support your research endeavors.

Experience accelerated research with Delve. Explore Delve's 14-day free trial and unlock the potential of qualitative analysis in a simplified manner. Get started today.

Qualitative Data Analysis Software | MAXQDA

All-in-one qualitative data analysis software, start your free trial.

Free MAXQDA trial for Windows and Mac

Your trial will end automatically after 14 days and will not renew. There is no need for cancelation.

Unlock the full potential of your qualitative research with the leading Qualitative Data Analysis Software

MAXQDA is the most user-friendly choice for your qualitative data analysis needs and is considered as one of the best qualitative data analysis software . It is designed to work with a wide range of data types, including text, audio, and video, and offers a variety of powerful tools for qualitative data analysis. Whether you’re looking to code and classify data , visualize patterns and themes, or perform mixed-methods , or quantitative content analysis, MAXQDA makes it easy to get the insights you need for your qualitative data analysis.

Document viewer

Your analysis.

All-in-one Qualitative Analysis Software developed by and for researchers

MAXQDA is the go-to software for managing and analyzing your qualitative research. Developed by and for researchers, it offers a wide range of powerful tools for managing your research project, analyzing data and collaborating with team members. With its user-friendly interface, step-by-step free tutorials and comprehensive documentation, it’s the perfect choice for both experienced and novice qualitative researchers. MAXQDA streamlines the qualitative data analysis process , giving you more time to focus on interpreting and understanding your data, rather than struggling with complicated software.

Developed by and for researchers – since 1989

Having used several qualitative data analysis software programs, there is no doubt in my mind that MAXQDA has advantages over all the others. In addition to its remarkable analytical features for harnessing data, MAXQDA’s stellar customer service, online tutorials, and global learning community make it a user friendly and top-notch product.

Sally S. Cohen – NYU Rory Meyers College of Nursing

Qualitative Data Analysis is Faster and Smarter with MAXQDA

MAXQDA makes qualitative data analysis faster and easier than ever before. It offers a wide range of analysis methods, including Grounded Theory , qualitative content analysis , group discussions , discourse analysis , Mixed Methods , and case and field studies . Its user-friendly 4-Window Interface provides quick access to powerful tools and functions, streamlining the data analysis process. Additionally, MAXQDA is the only leading Qualitative Data Analysis software that is 100% identical on Windows and Mac , providing a consistent and seamless analysis experience.

MAXQDA is the ultimate qualitative data analysis software, with its ability to seamlessly import all types of qualitative data making it the perfect tool for managing and analyzing your research project. With MAXQDA, you can easily import a wide range of data types such as text, interviews, focus groups, PDFs, web pages, spreadsheets, articles, e-books, bibliographic data, videos, audio files, and even social media data. Organize your data into groups, link relevant quotes to each other, use MAXQDA’s powerful tools to facilitate your qualitative analysis, and share and compare work with your team members. The project file stays flexible allowing you to expand and refine your category system as you go, ensuring your research is tailored to your needs.

User-Friendly Tools for Qualitative Coding

Utilize a variety of tools such as codes, colors, symbols, and emoticons to mark important information in your data. With MAXQDA, you can create codes with just one click and apply them quickly via drag & drop. The software’s Text Search tools allow you to explore your material without coding or reading them first. You can also search for keywords and automatically code them with just a few clicks. Organize your thoughts and theories in memos that can be linked to any element of your project. Retrieve your coded segments with one click or use MAXQDA’s powerful summary tools to test and develop new theories. Make the most of your time with MAXQDA, the #1 qualitative analysis software

Organize Your Qualitative Data with MAXQDA’s Memo Tools

As you perform your qualitative analysis, MAXQDA allows you to capture ideas and insights by creating memos to store research questions, objectives, and paraphrasing passages into your own words. The software’s memo feature also allows for easy creation of audit trails by attaching memos like post-it notes to text passages, texts, document groups, images, audio/video clips, and codes. With the unique MAXQDA memo manager and lexical search function, you have immediate access to every single memo at any time, making it easy to stay organized and on top of your research. With MAXQDA, the leading qualitative analysis software, your data organization is made simple.

Text Search and Autocoding Tools

When analyzing large amounts of text for a qualitative study, MAXQDA’s Text Search tools can be of great help. These tools allow you to explore your documents without having to manually read or code them first, by searching for keywords or concepts that are important to your analysis. With just a few clicks, you can automatically code these keywords, creating document variables that can be used for searching and retrieving specific segments. Additionally, MAXQDA’s powerful Coding Query feature allows for in-depth analysis of the combination of activated codes in various ways, making it a valuable tool in the qualitative data analysis software toolkit.

Visual Text Exploration

When it comes to conducting a qualitative data analysis, the software you choose can make a big difference in the ease and efficiency of your research. MAXQDA is a powerful and versatile qualitative data analysis software that is well-suited for analyzing both small and large sets of text. The software’s Interactive Wordtree feature is a particularly powerful tool, visualizing all the combinations that lead to or from any word of your choice and providing a detailed display of frequencies. This feature can provide new and fascinating perspectives even on texts you know well and allows for a comprehensive overview of those you don’t. Furthermore, MAXQDA’s Text Search tools and Coding Query feature allow you to search for keywords, concepts or certain segments and analyze the combination of activated codes in different ways.

A lot more than just a Qualitative Data Analysis Software

Quantitative aspects can also be relevant in qualitative data analysis, and MAXQDA as a leading qualitative data analysis software, offers a wide range of tools specifically designed to facilitate quantitative content analyses. These include tools for word frequency analysis, visual text exploration, content analysis, vocabulary analysis, and dictionary-based analysis that help researchers analyze terms and their semantic contexts in a quantitative way. With MAXQDA, you can easily display frequencies of individual words or word combinations in tables, visualize them in the Interactive Wordtree, or use the Keyword-in-Context function to transfer the textual contexts of selected words into a clear table, among other features.

Visualize your qualitative data

MAXQDA’s wide range of visual tools for qualitative data analysis allows you to create stunning visualizations to analyze your material and gain insights from your data. From codelines to code clouds and concept maps, these tools provide a range of options to help you explore and understand your data in new ways. With the interactive connection between your visualizations and your MAXQDA data, you can easily switch between different perspectives and never lose sight of the big picture. Additionally, you can export your visualizations in various formats to enrich your final report and share your findings with others. These visual tools in MAXQDA make it a powerful software for qualitative data analysis and mixed methods.

AI Assist: Qualitative data analysis software meets AI

AI Assist – your virtual research assistant – supports your work with various tools. Besides automatic transcription of audio and video recordings in different languages, AI Assist simplifies your work by automatically analyzing and summarizing elements of your research project and by generating suggestions for subcodes. No matter which AI tool you use – you can customize your results to suit your needs.

Free tutorials and guides on qualitative data analysis software

MAXQDA offers a variety of free learning resources for qualitative data analysis, making it easy for both beginners and advanced users to learn how to use the software. From free video tutorials and webinars to step-by-step guides and sample projects, these resources provide a wealth of information to help you understand the features and functionality of MAXQDA. For beginners, the software’s user-friendly interface and comprehensive help center make it easy to get started with your data analysis, while advanced users will appreciate the detailed guides and tutorials that cover more complex features and techniques. Whether you’re just starting out or are an experienced researcher, MAXQDA’s free learning resources will help you get the most out of your qualitative data analysis.

Free MAXQDA Trial for Windows and Mac

Get your maxqda license, compare the features of maxqda and maxqda analytics pro, faq: qualitative data analysis software.

MAXQDA is widely considered to be one of the best qualitative data analysis software on the market. It’s developed by researchers and offers a wide range of features and tools that allow researchers to easily organize, analyze and interpret qualitative data. With MAXQDA, users can import and work with a variety of file formats including text, audio, and video files. The software also provides advanced coding and categorizing capabilities, as well as visualization options for data analysis.

Additionally, MAXQDA has a user-friendly interface and offers a variety of tutorials and support resources to help users get the most out of the software. Overall, MAXQDA’s comprehensive set of features and ease of use make it the best choice for qualitative data analysis.

MAXQDA offers a wide range of tools for analyzing qualitative data, some of the most commonly used include:

• Coding : MAXQDA allows users to assign codes to segments of text, audio, or video files, and then use these codes to analyze the data.
• Memo : This tool allows users to create notes and reflections on the data, which can be used to help develop and refine coding schemes.
• Retrieval : MAXQDA provides several options for searching and retrieving data, such as keyword search, Boolean search, and proximity search.
• Visualization : The software offers a variety of visualization options, including word clouds, concordance lines, and code co-occurrence matrices, which allow users to quickly and easily identify patterns and connections in the data.
• Statistics : MAXQDA provides several statistical tools to analyze data, including frequency lists, crosstabs, and chi-square tests, which allow users to explore patterns and relationships in the data.
• Collaboration : MAXQDA also allows multiple users to work on the same project simultaneously and share the work.
• Importing and Exporting : MAXQDA can import and work with a variety of file formats including text, audio, and video files, and also export data to different formats such as Excel, SPSS, R, etc.

These are some of the most commonly used tools in MAXQDA, but the software offers many more options for analyzing qualitative data, depending on the research design and the researcher’s needs.

Analyzing qualitative data involves several steps. The first step is to import your data into MAXQDA. This can include text, audio, and video files, as well as images and other types of multimedia. Once the data is imported, you will need to organize it into manageable chunks. This might involve breaking up text files into smaller segments, transcribing audio or video files, and so on.

The next step is to begin coding the data. This involves assigning codes to segments of the data that relate to specific themes or topics. Codes can be assigned manually or automatically, and you can use multiple codes to analyze the data. Once you have coded your data, you can then use retrieval tools to search for specific segments of text, audio, or video that relate to a particular code or theme.

MAXQDA provides several visualization options, such as word clouds, concordance lines, and code co-occurrence matrices, which allow users to quickly and easily identify patterns and connections in the data. With the data organized, coded, and retrieved, you can begin to analyze it. This might involve identifying patterns and themes, comparing different segments of data, and so on.

The software allows users to create notes and reflections on the data, which can be used to help develop and refine coding schemes. MAXQDA allows multiple users to work on the same project simultaneously and share the work. Finally, when your analysis is complete, you can export your results in a variety of formats, including Excel, SPSS, R, etc. It’s important to note that the process of analyzing qualitative data with MAXQDA can vary depending on the research question, design, and methodologies you are using.

There are many different qualitative data analysis methods that researchers can use to analyze their data, such as:

Grounded theory : This method involves developing a theory that emerges from the data itself. Researchers begin by collecting and analyzing data, and then use this information to develop a theory that explains the data. This method is often used in the social sciences to study complex phenomena such as social interactions, organizational processes, and so on. With Grounded theory, the researcher does not begin with a preconceived theory but rather allows the theory to emerge from the data. MAXQDA offers tools such as the memo function and the ability to create codes and subcodes, which can help researchers to identify patterns and themes in the data, and develop a theory that explains these patterns and themes.

Content analysis : This method involves analyzing the content of the data, such as the words or themes that appear in a text. Researchers can use content analysis to identify patterns and themes in the data, such as the frequency of certain words or themes. MAXQDA provides tools such as the word frequency and word cloud functions, which can help researchers to quickly and easily identify patterns and themes in their data. Additionally, MAXQDA allows the user to code and categorize the data, which makes it easy to identify and analyze recurrent themes or patterns.

Discourse analysis : This method involves analyzing how language is used in the data to construct meaning. Researchers can use discourse analysis to study how language is used in different contexts, such as in political speeches, media reports, or online forums. MAXQDA offers tools such as the Word Tree, which can help researchers to study the use of language in their data, and the memo function, which can be used to reflect on the data and its meaning.

Narrative analysis : This method involves analyzing stories or narratives in the data to understand how they are constructed and how they convey meaning. Researchers can use narrative analysis to study how individuals construct and understand their own experiences, or how groups or communities construct and understand their collective experiences. MAXQDA provides tools such as the memo function, which can be used to reflect on the data and its meaning, and the ability to create codes and subcodes, which can help researchers to identify patterns and themes in the data.

Ethnography : This method involves studying a culture or community by immersing oneself in the culture or community and observing and participating in their daily activities. Researchers can use ethnography to study how culture or community shapes the experiences of individuals and groups. MAXQDA provides tools such as the memo function, which can be used to reflect on the data and its meaning, and the ability to create codes and subcodes, which can help researchers to identify patterns and themes in the data.

Case study : This method involves studying an individual or group in depth, often to understand a specific phenomenon or problem. Researchers can use case study to study how individuals or groups experience a particular phenomenon or problem. MAXQDA provides tools such as the memo function, which can be used to reflect on the data and its meaning, and the ability to create codes and subcodes, which can help researchers to identify patterns and themes in the data.

Phenomenology : This method involves studying the lived experiences of individuals or groups. Researchers can use phenomenology to study how individuals or groups experience the world around them. MAXQDA provides tools such as the memo function, which can be used to reflect on the data and its meaning, and the ability to create codes and subcodes, which can help researchers to identify patterns and themes in the data.

In summary, MAXQDA is a qualitative data analysis software that is compatible with all of these methods , and it provides a wide range of tools that can help researchers to analyze and understand their data.

Qualitative data analysis is the process of examining and interpreting non-numerical data, such as text, images, and audio recordings. The goal of qualitative data analysis is to identify patterns, themes, and insights within the data. This process typically involves coding and categorizing the data, and then using these codes to identify patterns and themes.

MAXQDA is widely considered as the best software for qualitative data analysis , it offers a wide range of tools to analyze and understand qualitative data, including the ability to code and categorize the data, identify patterns and themes, and create visual representations of the data. Additionally, MAXQDA is user-friendly and offers a wide range of free learning resources such as tutorials and webinars to help researchers of all levels to understand and use the software effectively. The software is developed by and for researchers, it is compatible with different research methodologies and offers a wide range of free resources to learn qualitative data analysis.

MAXQDA is considered as the best qualitative data analysis software for Mac. One of the key features of MAXQDA for Mac is that it is 100% identical and compatible with the Windows version, which makes it perfect for teamwork . This allows different people with different computers to work on the same project seamlessly, regardless of their operating system . This also provides researchers with more flexibility and allows them to work on their projects from different locations and platforms. Additionally, MAXQDA is user-friendly and offers a wide range of learning materials and tutorials to help researchers of all levels understand and use the software effectively.

MAXQDA is considered as one of the best qualitative data analysis software for students . MAXQDA offers deeply discounted prices for students, which makes it a cost-effective option for students. Additionally, MAXQDA also offers a scholarship for young researchers that provides free access to the software and training. Furthermore, MAXQDA organizes an annual international user conference, providing students with an opportunity to learn from experienced qualitative researchers , network with others in their field and stay up-to-date on the latest developments in qualitative data analysis.

MAXQDA is designed with ease of use in mind, making it a qualitative data analysis software that is accessible for students of all levels . It offers a comprehensive range of free learning resources in various formats, including videos and written guides, which are tailored to help students understand and effectively utilize the software’s various features and functionalities.

You are currently viewing a placeholder content from Brevo . To access the actual content, click the button below. Please note that doing so will share data with third-party providers.

You need to load content from reCAPTCHA to submit the form. Please note that doing so will share data with third-party providers.

You are currently viewing a placeholder content from Facebook . To access the actual content, click the button below. Please note that doing so will share data with third-party providers.

• UNC Libraries
• HSL Subject Research
• Qualitative Research Resources
• Qualitative Software for Coding/Analysis

Qualitative Research Resources: Qualitative Software for Coding/Analysis

Created by health science librarians.

• What is Qualitative Research?
• Qualitative Research Basics
• Special Topics
• Training Opportunities: UNC & Beyond
• Help at UNC

About this Page

Acquiring software, coding software, training available at the odum institute.

• Software for Audio, Video, Online Surveys
• Finding Qualitative Studies
• Assessing Qualitative Research
• Writing Up Your Research
• Integrating Qualitative Research into Systematic Reviews
• Publishing Qualitative Research
• Presenting Qualitative Research
• Qualitative & Libraries: a few gems
• Data Repositories

Why is this information important?

• Once you've collected and formatted your data, you'll need to analyze it, and most likely to code it.
• Software on this page facilitates coding all types of data, including text, audio, and video

On this page you'll find:

• software that allows you to code video, audio, and textual data
• resources that will help you learn to use the software
• information on how to acquire or use it through UNC*

*UNC provides access to some software packages for its affiliates, but the versions available on UNC computers are not always the most recent. UNC affiliated users can access information about acquisition of many types of software through UNC Software Acquisition .  Procedures for obtaining software will vary depending on the license agreement.  Discounts to UNC affiliated users are often available through these links.

Significant discounts are often available, especially to students, via the websites for these software packages.

Note: maxqda offers a free course license covering instructor and students for verified research methods focused courses:  https://www.maxqda.com/maxqda-course-license, many packages offer free trial versions (terms vary). .

See UNC Odum Institute, which supports QSR NVivo , ATLAS.ti , MAXQDA and a web-based program called Dedoose : qualitative data analysis software .

Note that most of these software packages offer educational discounts and very steeply discounted student licenses (proof required).  In addition, some will arrange for free or very inexpensive course licenses.

Free trial version (unlimited time; fully functional, project size limits): http://atlasti.com/free-trial-version/

Available at UNC:

• Odum Institute, second floor of Davis Library
• Virtual Lab

Starts with Free 1-month trial (then pay by the month for the months you will use): http://www.dedoose.com/signup

Free course licenses covering instructor and students for duration of a verified, research methods-focused course: https://www.maxqda.com/maxqda-course-license

Free 14-day trial (includes all the features of MAXQDA Analytics Pro ( compare product features )  : https://www.maxqda.com/trial

• Odum Institute , second floor of Davis Library

Free 14-day trial (fully functional; you can switch among editions during trial): https://www.qsrinternational.com/nvivo/trial

Check UNC Software Acquisition site for special UNC affiliated user pricing. Note terms and version.  

• Library Data Services , second floor of Davis Library
• HyperRESEARCH
• Sign up for a Qualtrics account at UNC here.
• This is a free web-based program designed for scholars who work with texts. It's not clear how many people use it to code, but it has various querying and annotation/automatic annotation functionalities.

The Odum Institute at UNC provides training and consultation on the selection and use of these and other tools:

• Qualtrics (for online surveys)

Paul Mihas , 962-0513, is available for consultation about these packages. He can help you decide which might be of use in your particular research and can provide assistance with its application. He also offers short courses on some of the text analysis programs. See the current Odum Institute short course schedule, or contact Paul to arrange a customized presentation to graduate or undergraduate classes and other special audiences.

Online Software Tutorials

The following links lead to online video trainings created by the companies who produce these programs. Note that HyperRESEARCH also has a series of hands-on tutorials embedded in the software, which you should be able to use if you have a license.

• << Previous: Help at UNC
• Next: Software for Audio, Video, Online Surveys >>
• Last Updated: Jul 28, 2024 4:11 PM
• URL: https://guides.lib.unc.edu/qual

AcademiaOS: Automating Grounded Theory Development in Qualitative Research with Large Language Models

AcademiaOS is a first attempt to automate grounded theory development in qualitative research with large language models. Using recent large language models’ language understanding, generation, and reasoning capabilities, AcademiaOS codes curated qualitative raw data such as interview transcripts and develops themes and dimensions to further develop a grounded theoretical model, affording novel insights. A user study (n=19) suggests that the system finds acceptance in the academic community and exhibits the potential to augment humans in qualitative research. AcademiaOS has been made open-source for others to build upon and adapt to their use cases.

Keywords  “Large Language Models”, “Software Design”, “Information Retrieval”, “Research Automation”, “Theory Development”

1 Introduction

Qualitative researchers are confronted with tedious and costly language tasks when making sense of interview or focus group transcriptions, reports, policies, field notes from observational research, diaries, case studies, and other sources. Transcribing and coding a typical interview takes several hours ( Pope et al., ( 2000 ) ; Barrett and Twycross, ( 2018 ) p. 63). A transcript or set of codes is often just the beginning, as the researcher tries to make sense of the raw data and transform it into something useful to gain insight and knowledge and develop theories that may describe patterns and phenomena.

Qualitative data may be collected through various tools, while purposive sampling directs the research ( Chun Tie et al., ( 2019 ) , p. 3). Interviews are a direct and easy way of exploring phenomena, from open, unstructured formats that allow researchers to dive deeper into studied participants’ narratives and experiences to more rigidly structured formats, essentially questionnaires, that provide more control to the researcher. Interviews are usually recorded and transcribed for further processing ( Barrett and Twycross, ( 2018 ) p. 63). A more relaxed way of studying subjects’ views is focus groups, where the researcher speaks to a small group of study participants to guide the conversation and debate about a given topic and to create rich data in the form of notes or transcription ( Kitzinger, ( 1995 ) p. 301). Another qualitative data collection methodology, prevalent primarily in ethnography, is field observation, where the researcher observes study subjects in a natural setting ( Emerson et al., ( 2001 ) , p. 352). ( Emerson et al., ( 2001 ) , pp. 356 - 358) describe generating data from ethnographic qualitative research as a process, starting with a researcher’s mental notes from immersing in the situation, followed by writing down jotted notes, to use as support for later generated, more extensive field notes. Ethnographic research also often builds on diaries and written notes, while organizational research might build on case studies, reports, policies, and other secondary sources. The bandwidth of qualitative data sources is broad, but most are textual or have established ways to transform them into textual data (i.e., transcribing).

Researchers often follow established coding practices to manage large volumes of unstructured textual sources. Coding often involves systematically generating a codebook ( Weston et al., ( 2001 ) ) to code transcriptions. Another popular approach is the "Gioia method" ( Gioia et al., ( 2013 ) ), where the researcher extracts emerging patterns and concepts from the source documents directly to aggregate and interpret them only in the following steps. These developed codes can then be further used for qualitative data analysis and theory development. The notion of developing theoretical models from data is called grounded theory development ( Chun Tie et al., ( 2019 ) ).

Gioia et al., ( 2013 ) define a transparent process for analyzing qualitative data to develop theoretical models from interviews. Their process is meant to move a researcher from raw qualitative data to increasingly abstract conceptual categories, starting with initial coding, where a researcher codes and underlines relevant concepts in the data, resulting in an extensive list of first-order concepts still stated in the language of the source document. They then use these first-order concepts to produce a list of more abstract second-order themes that try to encapsulate the idea of the first-order codes in more academic language. Lastly, they aggregate the second-order themes into even more abstract "aggregate dimensions." These are then used as the basis for developing theories. Gioia et al., ( 2013 ) mention the importance of understanding the dynamic relationships between these concepts but have yet to offer a concrete methodology to get to these. They assume that by following this "Gioia method," a researcher has familiarized themselves well enough with the underlying literature to understand these relationships.

Another approach to grounded theory development is the Eisenhardt, ( 1989 ) method, which focuses on constructing models from case studies. This approach starts with a within-case analysis to gain familiarity with the data and generate a preliminary theory. From there starts a highly iterative process, which Eisenhardt, ( 1989 ) calls "Shaping Hypotheses," iteratively comparing data and developed constructs and verifying that the emergent relationships between the developed constructs fit with the evidence in the data. They treat case studies as replications of experiments, either strengthening or weakening a hypothesis.

Structured approaches to qualitative analysis and theory development, such as those introduced by Gioia et al., ( 2013 ) and Eisenhardt, ( 1989 ) , were criticized for being used as mere "templates," often oversimplifying or ignoring the underlying methodological assumptions to fit in cases where those assumptions do not hold ( Gioia et al., ( 2022 ) , p. 241) or that using these templates limit methodological innovation in qualitative research ( Gioia et al., ( 2022 ) , p. 242). Even Gioia emphasizes that the methodology named after him should not be understood as a "cookbook" but as a tool adapted to each research context. He highlights the importance of researchers accounting for informants’ interpretations and constructions of reality in their reporting and not merely applying the methodology as a rigid framework ( Gioia et al., ( 2022 ) , p. 235). Building on the existing literature, it is clear that structured approaches like those of Gioia et al., ( 2013 ) and Eisenhardt, ( 1989 ) provide a framework for grounded theory development. However, they also highlight the necessity for flexibility and adaptation in qualitative research. Qualitative research tasks, both data collection and analysis, are time-consuming and expensive and limit the empirical data that a single research team can study. Kindsiko and Poltimäe, ( 2019 ) support this notion by outlining that sample size in empirical research depends on funding and the size of the research team. However, Bowen, ( 2008 ) outlines how the sample size influences research validity and suggests limiting sample size by saturation, i.e., stopping the addition of more interviews, case studies, or other samples when those do not add significant new information. Now, how do we add research rigor by increasing sample size while keeping manual effort low? The answer might be found in computational automation.

In quantitative research, automating data preparation and theory development is an actively researched topic under names such as "data mining" or "machine learning," where computer programs learn from observations to develop mathematical models, allowing them to estimate future instances in a positivist paradigm. Qualitative research problems, however, come with less structured or codifiable information and rely on the knowledge and interpretation of the researcher. At the same time, with the rise of large language models (LLMs), we have access to a technology platform, shifting the paradigm of computational understanding and reasoning on textual data to a level close to humans, paired with extensive general knowledge. This new technology platform presents an opportunity to simulate well-defined research processes at scale. Tasks such as coding 100 interview transcripts are time-consuming for a single researcher. The hypothesis is that with the proper setup, LLMs can process all transcripts in parallel within a few minutes. A researcher in the field of organization theory might consider using two or three case studies to develop a theoretical model. When finding empirical evidence in case studies is an automated, parallelizable process, the barrier to using 20 - 30 different case studies is drastically minimized, offering opportunities for more statistically relevant qualitative studies.

Thus, the potential for automating parts of the qualitative research process with LLMs is ripe for exploration. This paper explores the following research question: "How can a foundational open-source platform be effectively designed and implemented to leverage large language models to automate grounded theory development?". To that end, AcademiaOS is proposed and implemented as an open-source platform for automating or augmenting grounded theory development tasks such as coding, dimension aggregation, and theory development. AcademiaOS offers the scientific community a new methodology for conducting qualitative research that is transparent, accessible, and extensible (through its open-source character) and allows for broader evidence through the cost-effectiveness of parallelizing analysis of multiple qualitative sources simultaneously. This system could have a far-reaching impact in the social sciences, particularly in organization theory, but also in other disciplines where qualitative data is relevant.

The rest of this paper describes AcademiaOS and the technology behind it in more detail. In addition, an exploratory survey has been conducted to learn how students, professionals, and researchers use AcademiaOS and to guide future development. The platform is made open-source on GitHub under the MIT license, and a running instance is hosted on academia-os.org.

2 Earlier Work

There have been attempts to automate qualitative analysis. Berente et al., ( 2019 ) make an effort to develop a theoretical process for computationally intensive grounded theory development, proposing a theoretical, computational methodology to automate the following four steps for grounded theory development: (1) Sampling and data collection, (2) synchronic analysis, (3) lexical framing and (4) diachronic analysis using artificial-intelligence-based tools. They describe the computational process as evolving around a predefined but dynamic lexicon rather than synchronously "coding" emerging concepts. They propose to mine concepts using taxonomies.

Marathe and Toyama, ( 2018 ) discuss the possibility of automating the coding of interviews based on predefined human-annotated codebooks. Similar approaches have been implemented by Lennon et al., ( 2021 ) , according to their own analyses resulting in human-level accuracy. Rietz and Maedche, ( 2021 ) propose a semi-automated supervised machine-learning solution that learns coding rules from human annotators and applies them to a broader dataset. Still, defining rules or annotating a codebook beforehand assumes the researcher already has assumptions about the patterns in the analyzed qualitative literature. Furthermore, the academic papers mentioned above used old machine-learning techniques and ignored LLMs, while some commercial platforms are slowly adopting them. The commercial platform ATLAS.ti, ( 2023 ) announced test versions of their automated coding features in early 2023, splitting qualitative literature into paragraphs and coding them one by one using OpenAI’s LLMs. Other commercial platforms like elicit.org emerged, primarily using LLMs to automate literature review processes. Still, more is needed to know about how researchers use these new AI features on those platforms. Also, these applications automate only small portions of qualitative research processes and have yet to dive into the field of automating grounded theory development. This leads to the question of whether grounded theory development can be automated with LLMs.

3 Large Language Models

Large language models (LLMs) are a new technology platform based on transformer models, pre-trained on large datasets using self-supervision, encoding general and transferable knowledge in billions of parameters Roberts et al., ( 2020 ) . Unexpected capabilities such as reasoning and interaction emerged from learning "simple" next-token prediction at scale. These pre-trained foundation models are often fine-tuned to follow instructions ( Ouyang et al., ( 2022 ) ), to return structured output, or to be conversational (as seen with ChatGPT). While older models such as BERT would generally be regarded as LLM, in this paper, the term is exclusively used for models with a performance similar to or better than the GPT-3 base models. LLMs have been popularized and mass-adopted with the recent release of ChatGPT at the end of 2022. They have been applied to automate processes throughout industries ( Wulf and Meierhofer, ( 2023 ) , p. 4).

An inference interaction with an LLM typically consists of a natural language prompt (input) and completion (response). In OpenAI’s conversational models used throughout this paper (GPT-3.5 and newer), the inference prompt may consist of multiple "messages": generic system messages that set the frame and a history of user and assistant messages (see Appendices 1-11 for examples).

Without the need for fine-tuning, LLMs exhibit the ability to learn and generalize from information in the inference prompt ( Brown et al., ( 2020 ) ). One-shot or few-shot learning refers to passing samples in the prompt, whereas zero-shot learning refers to providing no samples but having the model complete an explicit instruction. This type of inference contrasts with common task-specific fine-tuning and is commonly called "in-context learning" ( Dong et al., ( 2022 ) ).

Although being pre-trained, LLMs store tremendous amounts of implicit knowledge in their parameters, that knowledge remains limited in its depth and currency and requires costly training to update. Therefore, augmenting the LLM inference with an information retrieval system, an architecture commonly called "Retrieval-Augmented Generation" (RAG), has been shown to reduce hallucination and improve factualness and interpretability ( Lewis et al., ( 2020 ) ). As general models, LLMs can measure semantic similarity between two text strings. Their similarity can be calculated computationally efficiently using cosine similarity on their LLM-internal vector representation. RAG uses this straightforward way of information retrieval to concatenate retrieved, relevant text for in-context learning ( Lewis et al., ( 2020 ) ). Augmenting LLM inference with information retrieval from raw input documents may help automate theory development.

To explore the current possibilities of automating grounded theory development with LLMs, I propose, develop, and test a piece of software that orchestrates LLM inferences with human supervision. AcademiaOS is a platform for qualitative researchers to automate their grounded theory development. The platform guides the user through a predefined process, and while most of the data analysis and theory development parts are automated, the user owns the supervision and control. To ensure user privacy and high maintainability, for potential future developers and open-source contributors to not worry about frontend-backend interaction, most of the computation is performed locally in the browser, consuming external APIs such as the OpenAI developer platform for LLM inference directly.

4.1 Data Curation

Qualitative research is a broad field working with various qualitative information sources, from interviews over policies to organizational case studies. To ensure versatility, the platform affords users to curate their source documents in multiple ways. If the user already has a corpus of curated sources, they can directly upload one or many source documents. The system extracts textual information for further use directly from documents in PDF, JSON, or TXT format. To support scanned PDF documents, the system pre-processes problematic PDF files by applying optical character recognition via Adobe PDF Services. Every file is transformed into a text string and handled as an individual source document.

A second option helps the user curate relevant academic literature from free-text search. The search term is used to retrieve academic literature from the SemanticScholar search engine that indexes more than 200 million academic papers. To interface with the SemanticScholar REST API, SemanticScholarJS was introduced as an open-source TypeScript library and published under the MIT license. SemanticScholar returns at most 100 papers, which are then vector-embedded using OpenAI’s text embeddings and re-ranked according to their abstracts’ semantic similarity to the initial search query and correspondingly re-ranked. Any papers without an abstract are filtered out, resulting in a few documents relevant to the user’s search query.

4.2 Data Coding

Assuming that the user might have an idea about their research’s direction, the platform affords the user to add a free-text remark or choose from an LLM-generated research question, which is used for in-context learning in the following inference prompts. This interactivity respects the expertise of the researcher while providing AI-assisted efficiency.

Following the Gioia method ( Gioia et al., ( 2013 ) ), the system initializes a three-step data analysis process. Implementing the Gioia method aligns the platform with established qualitative research practices, lending academic rigor to the process. This structured approach facilitates the systematic transformation of raw data into initial codes, second-order themes, and aggregate dimensions, used later for grounded theory development.

First, the system creates initial codes from the raw documents. Initial codes are short text strings describing emergent themes, concepts, and patterns in the language of the raw document. To that end, every input document is split into chunks of max. 10,000 characters to overcome context-size limitations and process arbitrarily large input. A chunk overlap of 50 characters was introduced to mitigate losing information in the intersection of two chunks. Every chunk is then inserted as context in the LLM inference prompt with a natural language instruction to return a JSON array. The output is then parsed and stored in a global array of initial codes.

Next, the initial codes are used to develop second-order themes. Second-order themes aggregate and interpret semantically similar initial codes and are expressed in a more abstract, academically correct language. To that end, the initial codes are split into reasonably-sized chunks and used in-context with a natural language instruction to return a JSON object of second-order themes as keys and arrays of related initial codes as values. This JSON object is again parsed and stored as a global object.

Finally, the second-order themes are used to develop aggregate dimensions. These aggregate dimensions are even more abstract, quantifiable concepts. Since second-order themes already limit the number of codes to a manageable count, further splitting into chunks is not necessary and the second-order themes are directly used in-context together with a natural language instruction to return a JSON object of aggregate dimensions as keys and arrays of related second-order themes as values. This JSON object is again parsed and stored as a global object for further use.

4.3 Theory Development

In the next step, the developed initial codes, second-order themes, and aggregate dimensions are used to develop grounded theories. ( Wacker, ( 1998 ) , pp. 364-367) found that to be considered ’good,’ a theory must exhibit the following virtues: uniqueness, conservatism, generalizability, fecundity, simplicity, internal consistency, empirical riskiness, and abstraction. To ensure some of those virtues, such as uniqueness, conservatism, and fecundity, the aggregate dimensions are used for the machine to "brainstorm" applicable theories that exist in the literature. As this brainstormed output is not intended to return accurate information but merely to scrutinize the obvious and increase serendipity, this step happens in a single inference prompt without information retrieval.

Next, to ground any interrelationships of concepts used in the final model in the data, the LLM first creates concept tuples, then uses these concept tuples for retrieval-augmented generation, searching for relevant paragraphs (chunks of max. 1000 characters, 50-character chunk-overlap) in the raw documents using cosine similarity search on their OpenAI vector embeddings and the concept tuples. Next, given the four most similar paragraphs, the LLM is prompted to generate a one-sentence summary about the relationship of a given concept tuple. This summary might include information about any evidence for correlation or causation, directedness, strength, mediatedness, conditional interaction, dynamics, or feedback loops.

Previously developed applicable theories, interrelationships, aggregate dimensions, second-order codes, and the user’s free-hand remarks are then fed into an LLM prompt, instructed to describe a comprehensive, novel theoretical model.

Next, another one-shot LLM inference transforms a given model description into a MermaidJS visualization. MermaidJS is a scripting language for creating flowcharts and similar graphics. Converting model descriptions into visualizations using MermaidJS not only aids in understanding complex theories but also provides a straightforward, communicative tool for sharing findings. First-order and second-order codes provided in the prompt are used to visualize evidence and support the notion of groundedness.

Finally, a last zero-shot LLM inference criticizes the developed model for novelty, conciseness, clarity, and theoretical insight. The user can then decide whether to start another modeling iteration with the critique fed into the modeling prompt, resulting in a feedback loop with human oversight.

4.4 Notes on the Technical Implementation

The system was initially considered a conglomerate of separate frontend and backend services. While this design decision would have come with the advantage of controlling any requests that go to the OpenAI developer platform, it would have slowed down development, maintenance, and hosting for the course of the project and beyond for future developers and open-source contributors. Thus, the decision was to run the application entirely in the browser. TypeScript as a primary programming language was chosen for its strong typing compared to vanilla JavaScript and, thus, higher maintainability and more robust code quality. Additionally, TypeScript’s extensive web development community offers abundant resources, libraries, and support, which is crucial for both the initial development and future iterations of the platform. Moreover, the decision to run the entire application in the browser, using ReactJS as a frontend framework and AntDesign as a component library, was driven by the need for an accessible, responsive, user-friendly interface. The ReactJS framework, through its component-based architecture, allows for efficient rendering and state management, which is essential in a dynamic environment where the state can frequently change through user interactions. The browser-based approach also aligns with the privacy concerns inherent in qualitative research. AcademiaOS minimizes the risks associated with data transfer and storage on remote servers by processing data locally on the user’s machine.

All results reported in this paper are based on OpenAI’s gpt-4-1106-preview model. To increase traceability and transparency, AcademiaOS affords users to easily set up a proxy to Helicone, an open-source monitoring platform specifically for LLM applications. Through Helicone, users maintain complete control and insight over their OpenAI API usage and the corresponding costs. In addition, Helicone logs all LLM inference requests. Monitoring is convenient during development to see where the LLM goes wrong and tune prompts. In addition, the platform affords saving and restoring developed codes and models for further development using JSON serialization and deserialization. This comes in especially handy during the development and testing phases to mitigate performing redundant steps and to facilitate a smooth development and testing workflow. The serialized data can also easily be shared between multiple users.

The field of large language models is actively researched and worked on. During this project, OpenAI and other vendors released new models with new capabilities. OpenAI’s most recent model, GPT-4-turbo, allows for larger context windows in a single inference prompt but also comes with an optional "JSON-mode" parameter, which ensures that the inference response is in a valid, parsable JSON format. Since many of AcademiaOS’ inference prompts expect data in a structured format (e.g., arrays of values), enforcing the JSON mode significantly increased the application’s robustness. Still, as LLM inference can occasionally yield invalid or unexpected results, rerunning the system on the same input often results in varied outputs, thereby increasing the probability of obtaining a correct response with subsequent attempts.

4.5 Notes on Epistemology and Ontology

Grounded theory development, as practiced by Gioia et al., ( 2013 ) or Eisenhardt, ( 1989 ) , generally follows a constructivist epistemology ( Charmaz and Thornberg, ( 2021 ) ). Constructivism in grounded theory proposes that knowledge is actively constructed through the interaction between the researcher and the researched subject. It argues for a subjective nature of reality and knowledge generation where the researcher’s perceptions shape the interpretative process ( Levers, ( 2013 ) , pp. 3-4). Further, grounded theory assumes that multiple realities of subjective constructions of individuals exist in a fluid nature of the reality of social interactions. As grounded theory development generates theories from observations of empirical data without previously established theories, grounded theory development is an inherently inductive approach.

Automating grounded theory development with large language models challenges epistemological and ontological assumptions. Epistemologically, Introducing LLMs adds an element of objectivity to the traditionally subjective approach. They process qualitative data in a way independent of a researcher’s biases. However, the researcher keeps the responsibility of interpreting and contextualizing the LLM’s output, preserving the constructivist nature of the process. At the same time, LLMs ontologically add a digital reality to the existing subjective realities. This digital reality offers an algorithmically created perspective on the processed qualitative data that can support or challenge the researcher’s interpretation.

4.6 Notes on Temperature, Robustness and Serendipity

To get an intuition on how model temperature changes the system’s output, outputs of gradual uniform temperature increase are recorded and qualitatively analyzed. To accommodate deterministic reproducibility, a seed parameter (324234) has been utilized with the employed gpt-4-1106-preview model for grounded theory development from a single podcast transcript from the How I Built This podcast.

Appendices 61 - 65 show that the three attempts with temperatures of 0, 0.5, and 1 resulted in consistent and robust outputs. In contrast, the attempt with a temperature of 1.5 became unstable, resulting in non-sensical text in the latter part of the model description and an invalid MermaidJS visualization. The attempts with temperatures of 0 and 0.5 resulted in internally consistent and integrated models. The attempt with a temperature of 1 produced a theoretical model with less integrity, meaning not or only loosely connected aspects and thus missing a consistent narrative. An increased temperature could, in this case, not be observed to lead to a higher degree of serendipity, that is, the quality of pleasant yet unexpected results. This might highlight the still objective, reproducible, and deterministic nature of grounded theory development and that randomness in the data analysis does not necessarily lead to better results. However, while providing a sense of intuition, the sample size of this experiment (n=1) might need to be larger to generalize.

An exploratory, qualitative survey has been conducted to assess user interaction with AcademiaOS and to guide future development. Researchers, professionals, and students with a background in qualitative research were chosen via convenience sampling for this evaluation. The participants (n=19), who were deliberately selected for their relevance to the platform’s intended user base and thus thought to yield the most informative and relevant data for assessing AcademiaOS, were provided with a link to a survey hosted on the Qualtrics platform.

The study’s methodology involved guiding participants through the AcademiaOS platform. This was achieved by direct interaction with the platform, through a video demonstration, or a combination, depending on the participant’s preference. Eight respondents reported testing the platform with a corpus of university policies on ChatGPT use that was provided alongside the survey. Other participants reported using datasets such as interview transcripts or academic papers from a basic literature review. Only 4 participants based their answers solely on the video demonstration (see Appendix 17). Following their experience with the platform, participants were asked to share their insights and opinions. The survey primarily consisted of open-ended questions, allowing for detailed and nuanced feedback.

The feedback encompasses various aspects of the platform, including user interface design, assessing the user’s initial interaction, feature exploration, and usability, but also the effectiveness of the system’s output and perceived impact on the user’s immediate research environment. Additional exploratory questions were asked about their current qualitative research processes and context.

Partial survey responses have been recorded. However, the 28 responses have been filtered and cleaned only to include 19 finished responses for further analysis. The other responses were very sparse, and it could not be trusted that they spent sufficient time familiarizing themselves with the platform. Another participant stated, "I don’t generally work with qualitative data," whose response was also filtered due to not belonging to the target population. Of the 19 residual responses, 14 were students, and the remaining participants were professionals and academic researchers (see Appendix 12). This might skew the responses to students’ perspectives. Peterson and Merunka, ( 2014 ) argue that convenience samples of students are problematic as they do not generalize to the general consumer population. However, they also explain that students might be an appropriate sample if they represent a population of interest. As the sampled students have at least some levels of experience in qualitative research, they sufficiently represent the studied group.

6.1 Status Quo

Participants were asked to reflect on their current qualitative research methodology. They reported using primary sources such as interviews, observations, surveys, and panels and secondary data sources such as case studies, reports, meta-analyses, historical data, reports, and expert opinions (Appendix 13).

Asked about their research methods, they reported data collection tools such as voice recordings, Microsoft Forms, or Google Forms for online surveys, data analysis methods such as thematic analysis, content analysis, literature review and case law analysis, empirical research, and knowledge discovery from existing datasets. One respondent mentioned testing qualitative data with quantitative research tools, while other respondents mentioned statistics and natural language processing techniques (such as named-entity recognition and topic modeling), hinting that there are tools to "quantify" qualitative data and that in research settings, the line between qualitative and quantitative research is often blurred. Interestingly, one respondent even mentioned using language models and the previously mentioned RAG architecture for their qualitative research (see Appendix 14). For systematic theory development, respondents mentioned grounded theory methodology, conceptual framework development, mind maps, and flowcharts, while some respondents see themselves merely as model users and less as creators or are unsure about their methodologies (see Appendix 15).

Inquiring about the AI tools they utilize in their research (see Appendix 16), some participants reported limited to no use of AI tools, not having used them or only using them rarely. Many respondents mentioned using ChatGPT with varying degrees of reliance and purposes such as brainstorming, idea generation, speeding up coding processes, or narrowing down searches. One respondent even noted the need for extensive fact-checking due to high error rates with ChatGPT. Other participants mentioned more specific AI and machine learning platforms and libraries: Fairseq, HuggingFace, Pytorch, OpenAI, AzureML, TensorFlow, scikit-learn, RapidMiner, KNIME, NLTK, SpaCy, Gensim and BERT. These reported AI tools underline the perceived importance of quantifying qualitative data through natural language processing.

6.2 Initial Interaction and Feature Exploration

The second part of the survey aimed to learn how participants perceived the platform’s initial interaction and feature exploration. The participants generally rated the platform as "somewhat easy" to learn, with some variance (see Appendix 18). Participants mentioned that the video helped them sufficiently understand how the system works. One participant suggested adding popups to guide the user, and another suggested that the affordances were not entirely clear: "[…] you should mention that the user can also upload non-pdf files […]" (appendix 19). Overall, participants reported finding it easy to find and use the option to search for academic papers (see Appendix 20) and to upload their own sources (see Appendix 21). However, they had more issues finding and using the options to "code" their sources (see Appendix 22) and to develop the theory (see Appendix 23). In general, participants found the user interface to be "somewhat" to "strongly" intuitive and user-friendly, with only one outlier who "strongly disagrees" (see Appendix 24).

As for difficulties navigating the platform (see Appendix 25), participants reported they expected more descriptive prompts and guidance: "I couldn’t find the coding help function," "the insert key thing was rather hidden," and "about the code part, didn’t really understand how to use it." One user noted that some buttons needed to be visible on mobile and experienced long loading times. Some improvement suggestions (see appendix 26) included "make it […] less technical", to add "filters for finding papers", to "add examples" and an "instructions page" to better guide users. Furthermore, better error handling with retry policies was suggested, together with the idea to "combine different searches or datasets in one coding tab." These feedback points are actionable and specific enough to guide the platform’s development.

6.3 Usability, Effectiveness, and User Satisfaction

Study participants seem to be "somewhat" to "extremely" satisfied with the coding process, with only one "extremely dissatisfied" outlier (see Appendix 27). Even more promisingly, participants think the system would create better codes than when they code manually (see Appendix 28). Only one participant thinks the system-generated output codes would be "somewhat worse" than their own. This is to be taken with a grain of salt as most respondents will have answered that only intuitively, without any actual comparison. Challenges in coding lie in multilingual documents (see Appendix 29). One respondent noted that when the source documents were not purposefully selected and had too much variation in their content, the machine could not generate meaningful codes: "[…] it was not able to catch that and make codes relevant to the research question". This seems to be an issue related to the paper retrieval and less so with the coding process. The average participant generally rated AcademiaOS as "very effective" in augmenting the coding process on qualitative data (see Appendix 30).

Regarding the theory development process, participants reported being somewhat to extremely satisfied (see Appendix 31). The respondents also reported that the system-produced output was perceived as better than potential manual development, with only three respondents each reporting that the system would do "somewhat worse" or "about the same" than when done manually (see Appendix 32). When asked about instances where the produced theory did not meet their expectations (see Appendix 33), one participant mentioned, "It was kind of complex, and I often didn’t really get where it was going with the theory.", indicating that they would have preferred a more straightforward model, while another one wrote "[…] theory seems to cover the content of the sources pretty generally but is not really about the research question I posed." indicating that there was a mismatch between the free-hand remarks and the model output. Despite these instances, respondents perceived the platform to be moderately effective to extremely effective, with a skew to the latter (see Appendix 34).

6.4 Participant-Reported Impact

When asked about whether AcademiaOS would impact their qualitative research process, most participants answered with "probably yes" to "definitely yes" (Appendix 35), mentioning reasons such as speeding up their research processes ("Much faster," "It will speed up the research," "It would make the coding and theory production much faster"), to act as a tool for inspiration ("Multiple draft iterations to inspire/shortcut the manual process," "I would use it to rapidly prototype theories […]", "[…] compare and maybe find things I missed before."), and as general research support ("It will urge many scientists to increase their throughput […] potential to mitigate the information retrieval and retention of humans", "[…] it would help me to link concepts easier", "Making it easier for me to do my research, especially in hours where I cannot concentrate that much") (see Appendix 36). When asked about how AcademiaOS would change the output of their academic research (see Appendix 37), participants noted "more varied and tested theories, better theories through more input ideas, more feedback," "use the models created as part of a clear visualization" and "[…] to be more reproducible". All respondents agree that AcademiaOS helps them ground their research on more data (see Appendix 41) and that it helps them conduct research faster (see Appendix 42). At the same time, most participants also agree that it helps them find more impactful and unexpected results (see Appendix 43).

However, participants also noted certain limitations such as ethical considerations ("It feels like cheating to me… I would not feel comfortable using it.", "It would make me feel too replaceable"), doubts about quality ("I also don’t quite trust the quality (mostly from experience with ChatGPT), I would always want to check it for what it misses.", "[…] it might fail to generate very latent codes") and doubts of potential (reinforced) biases ("[…] it may cause people to not properly look at the nuances of their interviews or papers", "Currently it is using a single AI model, which makes it difficult to rule out its biases.") (see Appendix 38). In addition, some participants fear being replaced by AI (see Appendix 40).

Respondents generally feel excited about the new possibilities that AcademiaOS provides (see Appendix 39). Most participants even stated they would continue using the system for their research (see Appendix 45). To an even greater extent, they would recommend AcademiaOS to their friends (see Appendix 46), indicating that they might know potential users who fit the intended target group better. Participants generally also feel excited about future versions of AcademiaOS (see Appendix 47), pointing out that despite the discussed doubts and limitations, the technology is promising for their research field.

7 Example Applications

This section presents a series of illustrative use-cases for AcademiaOS.

7.1 Modeling University Policies on ChatGPT Use

A corpus of 46 scraped public university policies on ChatGPT and LLMs were uploaded to AcademiaOS to build a theoretical model to answer the research question: "How can educational institutions adapt their academic integrity policies to effectively address the challenges posed by AI writing tools like ChatGPT?". From the 46 papers, AcademiaOS produced 1019 first-order codes, which in the next step were reduced and interpreted to 67 second-order themes and, in turn, reduced to 7 aggregate dimensions (see Appendix 49). After brainstorming applicable existing theories (see Appendix 50), the system then investigated the interrelationships between concept tuples (see Appendix 51) to generate the first iteration of a theoretical model (see Appendix 52). The system then critiqued the model (see Appendix 53) to produce the second iteration of the theoretical model (see Appendix 54). Note that the user is in control of the number of iterations.

The result was the Integrated Education Adaptation Framework for AI Readiness (IEAFAR) as a comprehensive model for educational adaptation to artificial intelligence. Its six dimensions, AI Integration and Educational Dynamics (AI-ED), Adaptive Compliance and Policy Evolution (ACPE), Academic and Instructional Resilience (AIR), AI-Driven Educational Innovation (ADEI), Ethical, Legal, and Societal Harmony (ELSH), and Collaborative Stakeholder Engagement (CSE) emphasize the importance of holistic, iterative processes in adapting to AI, with interconnected relationships among these dimensions. IEAFAR promotes stakeholder collaboration, focusing on continuous learning, flexible adaptation, and balancing innovation and ethical, legal, and societal considerations.

7.2 Exploring the “How I Built This” Transcript Dataset

The "How I Built This" podcast is a format interviewing innovators about the things (such as products or companies) they have created. The hypothesis is that AcademiaOS can explore the rich and extensive interview dataset to detect interesting patterns in how entrepreneurs start projects. The system coded the transcripts of 4 podcast episodes to 499 first-order codes, 35 second-order themes, and 7 aggregate dimensions (see Appendix 55). It then generated applicable theories and explored the interrelationships between concept tuples before generating the first iteration of the theoretical model. This time, the AI-generated the "Dynamic Entrepreneurial Synthesis Model (DESM)" (see appendix 56) grounded in the podcast transcripts.

The Dynamic Entrepreneurial Synthesis Model describes the multifaceted journey of business development, integrating personal growth with the development of innovative products. Community, market understanding, social responsibility, and strategic financial planning are central. Further, the model suggests that strong relationships, market traction, and effective leadership are core to successful entrepreneurship.

7.3 Modeling the Cardiovascular Health Effects of Alcohol

The following example is slightly different, as policies or interview transcripts are not uploaded. Instead, it starts with a free-text search for academic papers to further explore, code, and model the topic. AcademiaOS selected 26 academic publications from SemanticScholar to use for further processing. It then codes the abstracts of these publications to 395 first-order codes (see appendix 57), 35 second-order themes, and 7 aggregate dimensions. These codes are then used to create the first-iteration model (see Appendix 58), which gets critiqued (see Appendix 59) to create the second-iteration model (see Appendix 60). In this case, the system was able to create an easy-to-grasp model called "The Dynamic Socio-bio-psychological Model of Alcohol Impact (DSBPAI)," connecting the "environmental context grid" with the "individual health trajectory," facilitating new research angles. The model shows reciprocal feedback mechanisms and causal correlations, highlighting the multidimensionality of influences from molecular to societal scales.

8 Discussion

The following section critically examines the findings from the implementation and the user study of AcademiaOS. This discussion aims to contextualize these findings within the broader scope of existing research, address implications, acknowledge limitations, and suggest directions for future research. The primary objective of this study was to design and implement an open-source platform to automate or augment grounded theory development. An accompanying user survey was designed to assess the platform’s effectiveness. The findings suggest that the platform is well-received within the academic community. AcademiaOS’ capabilities in typically labor-intensive tasks such as coding qualitative data and developing theoretical models constitute a significant step in augmenting human researchers in qualitative research.

The user survey provides relevant insight into the target population’s opinion and experience with AcademiaOS. Respondent’s diverse use of primary and secondary qualitative sources and various data collection and analysis methods emphasize the multifaceted nature of qualitative research. The inclusion of AI tools such as ChatGPT and other natural language processing technologies highlights the trend toward integrating quantitative methods into qualitative research. This blurs the boundaries between traditional qualitative research and quantitative research. By leveraging technologies like AcademiaOS, researchers can uncover patterns and insights that might otherwise remain obscured due to the voluminous nature of qualitative data. This new technology could shift how qualitative research is conducted, making it more efficient and comprehensive while maintaining and following the established framework and corresponding research paradigms of grounded theory development ( Gioia et al., ( 2013 ) ; Eisenhardt, ( 1989 ) ). AcademiaOS embodies a pragmatic approach, joining the subjectivity of human interpretation with the efficiency and scale of LLMs.

The general satisfaction with the coding process and the belief that the system could generate better codes than manual coding is promising. However, participants also noted challenges in coding multilingual documents and dealing with varied content sources, suggesting that there is room for improvement in the system’s sensitivity to other data types. Also, the participant’s satisfaction with the theory development process and illustrated example applications such as policy or interview analysis appear promising. However, user feedback suggests that the system might still have issues aligning closely with a user’s research goals.

The reported potential impact of AcademiaOS speeding up research processes and providing inspiration is a significant positive outcome. However, ethical concerns and doubts about quality and bias indicate the need for a robust framework ensuring ethical use and quality control. The participant’s excitement about the technology’s potential and willingness to recommend and continue using the platform signals a positive outlook for AcademiaOS in the academic community.

9 Limitations

While AcademiaOS introduces a novel approach to automating grounded theory development, this work has several limitations. First, through its reliance on LLMs, the system inherits some of the common limitations those models exhibit. Chen et al., ( 2023 ) found that LLMs perform worse than common information retrieval systems in answering questions factually correctly, especially in a few-shot in-context learning context. The theory development use-case, however, is not per se a knowledge generation task that requires high levels of accuracy or informativeness, as long as those metrics are present enough together with coherency, relevancy, helpfulness, and validity, all measures where Chen et al., ( 2023 ) found good performance. As LLMs’ output is open, sometimes unexpected out-of-range completions, such as incorrect MermaidJS visualization script syntax or wrong JSON fields, can occur. This can only partly be mitigated by writing stricter prompts (e.g., specifying the output schema or providing a specific example). Kocoń et al., ( 2023 ) found that state-of-the-art AI solutions generally outperform current LLMs on common NLP tasks, suggesting that specialized models could also perform better on some functions where AcademiaOS employed LLMs, such as the coding process. A benchmarking of different technologies was not in the scope of this work. The inherent bias of models like GPT-4 ( Bubeck et al., ( 2023 ) , pp. 86 - 89) might pose challenges to sensitive topics, such as when working with protected attributes. However, since the idea of grounded theory development is to base any hypotheses on the curated source data, there is little room for biased interpretation, neither for human nor machine inference.

While the designed LLM-supported process allows for coding qualitative documents for grounded theory development at scale, documents such as interview transcripts and their antecedent codes might miss latent information and nuances that a researcher who conducted the interviews themselves might possess, immersing themselves more profoundly in the studied environment. An LLM can only partially compensate for that with the extensive general knowledge it draws on, potentially leading to misinterpretations or overgeneralizations in the developed theories. Therefore, qualitative research might develop to be a joint effort between human and machine inference. Jiang et al., ( 2021 ) studied human-AI interaction in qualitative research. They pointed out another possible limitation: researchers might be reluctant to have AI to eliminate the "uncertainty" from their research efforts. They argue that researchers value the inefficiencies in working with qualitative data and that mistakes in interview coding, for instance, lead to higher serendipity and new perspectives. Automation might be a hindrance in this process. However, survey participants reported expecting AcademiaOS to help them gain more unexpected results (see Appendix 43). Bouschery et al., ( 2023 ) explore the same aspect in product innovation teams whose methodologies are similar to those of academic researchers and found that those teams profit from larger problem spaces and solution spaces when working jointly with AI.

There are also data privacy concerns. AcademiaOS, in its current form, draws on the OpenAI developer platform for LLM inferences. Therefore, sensitive data not meant to be shared with external entities can not be processed with the proposed system for ethical and legal reasons. However, to ensure data privacy, the system can be modified to run on a self-hosted LLM (such as a Llama2 or a Mistral 7B instance), ensuring complete data control.

Another limitation is scope. AcademiaOS is primarily designed for qualitative research in fields such as organization theory and may not be as effective for other research areas where qualitative data plays a secondary role or where grounded theory development is not an appropriate methodology. Also, AcademiaOS is far from automating the entire qualitative research process that researchers should overly rely on. Instead, AcademiaOS is a tool supporting the researcher in understanding the data and modeling interesting patterns that might guide or inspire their qualitative research.

As for methodological limitations, the user survey was designed to be exploratory and might not give a representative image of AcademiaOS’ performance in the field. While the study gave informative and extensive subjective insight, the participant sample was too small to reach data saturation, and insights were given on initial impressions rather than on actual work using this new tool. Further research might be necessary to understand the technology’s impact more accurately.

10 Ethics, Risks, and Trustworthy AI

What follows is a critical reflection on the potential impact and systemic risks associated with using the tool in qualitative research. Autonomous systems are often criticized or feared for not aligning with human values. This is a complex problem, as it is hard to identify a correct set of values the AI should align with, living in a world of different moral stances, leaving the option to identify a common ground of values that would hold in a pluralist reality ( Gabriel, ( 2020 ) , pp. 14-16). This might also draw on political discourse on how to aggregate different stances (see, e.g., Rawls, ( 2017 ) ) or which universal values to agree on (e.g., the Universal Declaration of Human Rights). The European Commission et al., ( 2019 ) made an attempt to translate liberal European values into concrete guidelines for AI systems.

O’neil, ( 2017 ) introduces the concept of "Weapons of Math Destruction," arguing that algorithms, automation, and big data potentially lead to undesirable outcomes. She explores multiple effects that might make autonomous systems dangerous. Firstly, the author argues that while seemingly objective, these systems can amplify or perpetuate bias in the data they are fed. This might be problematic in fields where a biased system can lead to unfair outcomes. Secondly, O’Neil criticizes opaque algorithms and lack of transparency, which can lead to accountability issues. Thirdly, she emphasizes that algorithms, unlike human agents, can work at scale, affecting thousands of people at once. Lastly, she criticizes potentially destructive feedback loops.

I will argue that AcademiaOS is designed around trustworthy AI standards that aim to mitigate these kinds of destructive effects. Thiebes et al., ( 2021 ) identify five foundational principles of trustworthy AI that are largely compatible with established guidelines from public institutions, such as the Ethics Guidelines by the European Commission et al., ( 2019 ) : Beneficence, non-maleficence, autonomy, justice, and explicability. In the following, I will analyze AcademiaOS using these five principles.

Firstly, beneficence is defined as the quality of promoting the well-being of humans and respecting basic human rights ( Thiebes et al., ( 2021 ) ). European Commission et al., ( 2019 ) further specifies these as "fundamental rights," that is, respect for human dignity, freedom of the individual, respect for democracy, justice and the rule of law, equality, non-discrimination and solidarity, and citizens’ rights. AcademiaOS implicitly promotes the well-being of humans by promoting scientific discovery and, therefore, the advancement of knowledge and education. This helps researchers conduct rigorous research more efficiently and promotes broader access to qualitative research methods with minimal violation of individuals’ fundamental rights. According to Thiebes et al., ( 2021 ) , these qualities promote trusting beliefs such as benevolence, helpfulness, and purpose, adding to the notion of trustworthy AI.

Secondly, non-maleficence is the quality of preventing harm to people ( Thiebes et al., ( 2021 ) . That entails the protection of human dignity and mental and physical integrity. Galactica from Meta is a recent case study for malicious science communication with LLMs. Galactica is an LLM trained on scientific literature to produce corresponding content. It was shut down only three days after being opened to the public for being criticized for hallucinating false information while articulating it in a scientifically convincing way ( Heaven, ( 2022 ) ). This might have led to severe consequences, such as polluted journals with made-up "knowledge." Boiko et al., ( 2023 ) published another example of LLM-powered scientific discovery, specifically in chemical research. They outlined the risk of dual-use application, allowing non-scientists to synthesize dangerous and illegal substances by a simple prompt to the autonomous research agent. One could argue that AcademiaOS is prone to be misused in a scenario similar to the Galactica case, where an AI system autonomously publishes papers at scale and pollutes academic databases with false information. However, AcademiaOS is not an agent autonomously interacting with the world and creating harm on its own. In its current form, it is a mere tool controlled by a human researcher at every step. While AcademiaOS might lower the entry barrier to grounded theory development and thus also for potential misuse, through the still high computational cost, the necessary human component, and therefore time spent generating theoretical models with AcademiaOS, this is not an issue of scalable impact as O’neil, ( 2017 ) would have warned about. Furthermore, even with malevolent misuse, e.g., through the spreading of wrong information, the accountability question does not change to when done manually.

Other risks for harm, as pointed out by O’neil, ( 2017 ) , are reflected or amplified bias and potential perpetuation or destructive feedback loops. To illustrate this, consider a hypothetical scenario set in the realm of social sciences research in the 1950s. An AI system is employed to analyze social data. The AI, constrained by the prevailing societal norms and limited data of its time, could inadvertently reinforce existing biases. It might generate theories that perpetuate gender or racial stereotypes because the data of that era is heavily skewed. This could have significant ethical implications and potentially end in a destructive feedback loop. I would argue that this naïve empiricism is inherent in grounded theory development – whether automated or not. The notion of groundedness assumes that the curated input data offers an accurate account of the studied subject. Gioia et al., ( 2013 ) are very clear in their assumption that the informants (for example, the interviewees) are knowledgeable agents whom the researcher should try to capture an adequate account from. This naïve empiricism has been criticized before (e.g., Thornberg, ( 2012 ) ; Gioia et al., ( 2013 ) ), and there might be disciplines where other research methodologies with varying epistemological assumptions might be better applicable. Nonetheless, grounded theory development is an established and accepted methodology and in some disciplines through its transparency and replicability, even the dominant way of capturing informants’ accounts and representing data analysis. AcademiaOS is designed to follow the established grounded theory development process as closely as possible. Therefore, it is unlikely that AcademiaOS increases the risk inherent with naïve empiricism compared to the non-automated way. On the contrary, through the potentially decreasing cost of grounded theory development through automation, more data can be analyzed in smaller intervals, potentially balancing local biases and accounting for a more temporarily accurate picture of lived experiences. Thiebes et al., ( 2021 ) attribute these non-maleficence qualities to the trust beliefs of integrity, reliability, and process, supporting the notion of trustworthiness.

Thirdly, in the realm of trustworthy AI, autonomy is the quality of promoting human agency and control – and, therefore, restricting, where necessary, the autonomy of the AI system. Human agency revolves around the ability of users to make informed and autonomous decisions. AcademiaOS is designed to assist the researcher in their creative work but, through its design, ensures that the final decision-making power and interpretative control rests with the user. While AcademiaOS automates data analysis and theory development, it requires the user to curate the data, supervise and control the processes, and put its output into use. This human-in-command approach ensures the researcher decides how to use the system and its produced output and integrate them into their broader research agenda. At every step in the automated process, the researcher has the power to control and stop further processing, essentially putting a human in the loop, promoting human autonomy and, in turn, the notion of trustworthy AI.

Fourthly, Thiebes et al., ( 2021 ) define justice as the quality of amending past inequities, sharing the benefits of AI use, and mitigating new harms and inequities. LLMs are known to exhibit bias emerging from training data, underlying algorithms, labeling and annotation, product design decisions, and policy decisions ( Ferrara, ( 2023 ) ). It is, therefore, essential to use them responsibly. The approach of grounded theory development inherently constrains the interpretative freedom of the executing agent – whether human or machine – and thus leaves less room for bias than in an unconstrained environment. The human-in-the-loop approach affords real-time moderation. Researchers can detect and correct biased or incorrect responses ( Ferrara, ( 2023 ) ). Popular LLMs, such as those used by AcademiaOS, are constantly subject to thorough study of their biases (e.g., Zack et al., ( 2024 ) ). With its open-source character, AcademiaOS is transparent in its use of LLMs. It allows the researcher to be educated and to assess the appropriateness of using a potentially biased language model for their work. Furthermore, emphasizing user experience in the system’s development increases accessibility and allows less tech-savvy demographics to use AcademiaOS. Survey participants majorly confirm that AcademiaOS is easy to learn (see Appendix 18). Addressing these justice issues promotes the trust beliefs of integrity, reliability, and process and, therefore, again, the system’s trustworthiness ( Thiebes et al., ( 2021 ) ).

Fifthly, explicability is the quality of upholding interpretability ( Thiebes et al., ( 2021 ) ). The European Commission et al., ( 2019 ) further specifies that for an AI system to be considered transparent, it must be explainable, traceable, and clearly communicated. AcademiaOS’ open-source character promotes explainability by being transparent with its exact implementation. A transparent, stepwise presentation of the sub-results aims to explain and communicate how the machine comes up with the end result. The Helicone integration promotes traceability. Furthermore, AcademiaOS does not present itself as human in its communication, and users are not misled by the fact that they communicate with an AI system. These design choices on explicability contribute to the trust beliefs of competence, functionality, and performance ( Thiebes et al., ( 2021 ) ) and, therefore, further to the notion of trustworthy AI.

While AI systems pose new threats to human values, AcademiaOS addresses critical issues around beneficence, non-maleficence, autonomy, justice, and explicability to ensure its trustworthiness. This reflection may guide users and open-source contributors in developing and using the system appropriately and responsibly.

11 Conclusion

AcademiaOS marks a first tangible step in automating grounded theory development with large language models. The system develops theoretical models grounded in the curated qualitative raw data using a coding process borrowed from Gioia et al., ( 2013 ) and an iterative multi-prompt modeling process. This system demonstrates the feasibility and efficiency of employing LLMs to analyze and gain insight from qualitative data, which traditionally requires extensive human effort and time. A first-user survey (n=19) suggests great acceptance and potential within the academic community. Users appreciated the system’s ability to handle large volumes of data, providing insights that might be overlooked in manual analysis. However, the study also highlighted inherent limitations and risks that future iterations of the platform might be able to mitigate. The platform’s open-source nature and user-friendly design make it accessible and adaptable for various research contexts. While not replacing human researchers anytime soon, AcademiaOS serves as a trustworthy AI tool to augment and enhance qualitative research and a basis for future research.

• ATLAS.ti, (2023) ATLAS.ti (2023). Ai coding powered by openai. https://atlasti.com/ai-coding-powered-by-openai .
• Barrett and Twycross, (2018) Barrett, D. and Twycross, A. (2018). Data collection in qualitative research.
• Berente et al., (2019) Berente, N., Seidel, S., and Safadi, H. (2019). Research commentary—data-driven computationally intensive theory development. Information systems research , 30(1):50–64.
• Boiko et al., (2023) Boiko, D. A., MacKnight, R., Kline, B., and Gomes, G. (2023). Autonomous chemical research with large language models. Nature , 624(7992):570–578.
• Bouschery et al., (2023) Bouschery, S. G., Blazevic, V., and Piller, F. T. (2023). Augmenting human innovation teams with artificial intelligence: Exploring transformer-based language models. Journal of Product Innovation Management , 40(2):139–153.
• Bowen, (2008) Bowen, G. A. (2008). Naturalistic inquiry and the saturation concept: a research note. Qualitative research , 8(1):137–152.
• Brown et al., (2020) Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems , 33:1877–1901.
• Bubeck et al., (2023) Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 .
• Charmaz and Thornberg, (2021) Charmaz, K. and Thornberg, R. (2021). The pursuit of quality in grounded theory. Qualitative research in psychology , 18(3):305–327.
• Chen et al., (2023) Chen, L., Deng, Y., Bian, Y., Qin, Z., Wu, B., Chua, T.-S., and Wong, K.-F. (2023). Beyond factuality: A comprehensive evaluation of large language models as knowledge generators. arXiv preprint arXiv:2310.07289 .
• Chun Tie et al., (2019) Chun Tie, Y., Birks, M., and Francis, K. (2019). Grounded theory research: A design framework for novice researchers. SAGE open medicine , 7:2050312118822927.
• Dong et al., (2022) Dong, Q., Li, L., Dai, D., Zheng, C., Wu, Z., Chang, B., Sun, X., Xu, J., and Sui, Z. (2022). A survey on in-context learning. arXiv preprint arXiv:2301.00234 .
• Eisenhardt, (1989) Eisenhardt, K. M. (1989). Building theories from case study research. Academy of management review , 14(4):532–550.
• Emerson et al., (2001) Emerson, R. M., Fretz, R. I., and Shaw, L. L. (2001). Participant observation and fieldnotes. Handbook of ethnography , pages 352–368.
• European Commission et al., (2019) European Commission, S. et al. (2019). Ethics guidelines for trustworthy ai. Publications Office .
• Ferrara, (2023) Ferrara, E. (2023). Should chatgpt be biased? challenges and risks of bias in large language models. arXiv preprint arXiv:2304.03738 .
• Gabriel, (2020) Gabriel, I. (2020). Artificial intelligence, values, and alignment. Minds and machines , 30(3):411–437.
• Gioia et al., (2022) Gioia, D., Corley, K., Eisenhardt, K., Feldman, M., Langley, A., Lê, J., Golden-Biddle, K., Locke, K., Mees-Buss, J., Piekkari, R., et al. (2022). A curated debate.
• Gioia et al., (2013) Gioia, D. A., Corley, K. G., and Hamilton, A. L. (2013). Seeking qualitative rigor in inductive research: Notes on the gioia methodology. Organizational research methods , 16(1):15–31.
• Heaven, (2022) Heaven, W. D. (2022). Why meta’s latest large language model survived only three days online. MIT Technology Review. Last accessed December , 15:2022.
• Jiang et al., (2021) Jiang, J. A., Wade, K., Fiesler, C., and Brubaker, J. R. (2021). Supporting serendipity: Opportunities and challenges for human-ai collaboration in qualitative analysis. Proceedings of the ACM on Human-Computer Interaction , 5(CSCW1):1–23.
• Kindsiko and Poltimäe, (2019) Kindsiko, E. and Poltimäe, H. (2019). The poor and embarrassing cousin to the gentrified quantitative academics: What determines the sample size in qualitative interview-based organization studies? In Forum Qualitative Sozialforschung/Forum: Qualitative Social Research , volume 20, page 24. DEU.
• Kitzinger, (1995) Kitzinger, J. (1995). Qualitative research: introducing focus groups. Bmj , 311(7000):299–302.
• Kocoń et al., (2023) Kocoń, J., Cichecki, I., Kaszyca, O., Kochanek, M., Szydło, D., Baran, J., Bielaniewicz, J., Gruza, M., Janz, A., Kanclerz, K., et al. (2023). Chatgpt: Jack of all trades, master of none. Information Fusion , 99:101861.
• Lennon et al., (2021) Lennon, R. P., Fraleigh, R., Van Scoy, L. J., Keshaviah, A., Hu, X. C., Snyder, B. L., Miller, E. L., Calo, W. A., Zgierska, A. E., and Griffin, C. (2021). Developing and testing an automated qualitative assistant (aqua) to support qualitative analysis. Family medicine and community health , 9(Suppl 1).
• Levers, (2013) Levers, M.-J. D. (2013). Philosophical paradigms, grounded theory, and perspectives on emergence. Sage Open , 3(4):2158244013517243.
• Lewis et al., (2020) Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems , 33:9459–9474.
• Marathe and Toyama, (2018) Marathe, M. and Toyama, K. (2018). Semi-automated coding for qualitative research: A user-centered inquiry and initial prototypes. In Proceedings of the 2018 CHI conference on human factors in computing systems , pages 1–12.
• O’neil, (2017) O’neil, C. (2017). Weapons of math destruction: How big data increases inequality and threatens democracy . Crown.
• Ouyang et al., (2022) Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022). Training language models to follow instructions with human feedback. Advances in neural information processing systems , 35:27730–27744.
• Peterson and Merunka, (2014) Peterson, R. A. and Merunka, D. R. (2014). Convenience samples of college students and research reproducibility. Journal of Business Research , 67(5):1035–1041.
• Pope et al., (2000) Pope, C., Ziebland, S., and Mays, N. (2000). Qualitative research in health care: Analysing qualitative data. BMJ: British Medical Journal , 320(7227):114.
• Rawls, (2017) Rawls, J. (2017). A theory of justice. In Applied ethics , pages 21–29. Routledge.
• Rietz and Maedche, (2021) Rietz, T. and Maedche, A. (2021). Cody: An ai-based system to semi-automate coding for qualitative research. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems , pages 1–14.
• Roberts et al., (2020) Roberts, A., Raffel, C., and Shazeer, N. (2020). How much knowledge can you pack into the parameters of a language model? arXiv preprint arXiv:2002.08910 .
• Thiebes et al., (2021) Thiebes, S., Lins, S., and Sunyaev, A. (2021). Trustworthy artificial intelligence. Electronic Markets , 31:447–464.
• Thornberg, (2012) Thornberg, R. (2012). Informed grounded theory. Scandinavian journal of educational research , 56(3):243–259.
• Wacker, (1998) Wacker, J. G. (1998). A definition of theory: research guidelines for different theory-building research methods in operations management. Journal of operations management , 16(4):361–385.
• Weston et al., (2001) Weston, C., Gandell, T., Beauchamp, J., McAlpine, L., Wiseman, C., and Beauchamp, C. (2001). Analyzing interview data: The development and evolution of a coding system. Qualitative sociology , 24:381–400.
• Wulf and Meierhofer, (2023) Wulf, J. and Meierhofer, J. (2023). Towards a taxonomy of large language model based business model transformations. arXiv preprint arXiv:2311.05288 .
• Zack et al., (2024) Zack, T., Lehman, E., Suzgun, M., Rodriguez, J. A., Celi, L. A., Gichoya, J., Jurafsky, D., Szolovits, P., Bates, D. W., Abdulnour, R.-E. E., et al. (2024). Assessing the potential of gpt-4 to perpetuate racial and gender biases in health care: a model evaluation study. The Lancet Digital Health , 6(1):e12–e22.

12 Appendix

Appendix 1: first-order coding inference.

System Message:

You are tasked with applying the initial coding phase of the Gioia method to the provided academic paper. In this phase, scrutinize the text to identify emergent themes, concepts, or patterns. Your output should be a JSON object with an array of strings no longer than 7 words, each representing a distinct initial code in the language of the raw source. For example, your output should be in this format: {"codes": string[]}. Ensure to return ONLY a proper JSON array of strings.

[Raw document chunk] Perform initial coding according to the Gioia method on the given paper. Return a JSON object.

Example Response:

Appendix 2: Second-Order Coding Inference

You are tasked with applying the 2nd Order Coding phase of the Gioia method. In this phase, identify higher-level themes or categories that aggregate the initial codes. Your output should be a JSON-formatted object mapping each higher-level theme to an array of initial codes that belong to it. As a general example, "employee sentiment" could be a 2nd order code to 1st level codes "Positive feelings toward new policy" and "Sense of control" Your output should look like this, where the keys are the higher-level concepts: {"Some higher-Level theme": ["some initial code", "another initial code"], "Another higher-level theme": ["some initial code"]}.

Part of the initial codes are as follows: [First Order Codes]

Perform 2nd Order Coding according to the Gioia method and return a JSON object of 12 focus codes.

Appendix 3: Dimension Aggregation Inference

You are tasked with applying the Aggregate Dimensions phase of the Gioia method. In this phase, identify overarching theoretical dimensions (5-7) that aggregate the 2nd order codes. Your output should be a JSON-formatted object mapping each aggregate dimension to an array of 2nd order codes that belong to it. As a (probably unrelated) general example, "Policy Usability" could make for a good, quantifiable dimension. Your output should look like this, where the keys are the (quantifiable) dimensions: {"some dim": ["theme", "another theme"], "another dim": ["theme123"]}. Ensure that the aggregate dimensions are grounded in the themes and to return ONLY a proper JSON object.

The 2nd order codes are as follows: [Second-order codes]

Perform aggregation into theoretical dimensions according to the Gioia method and return a JSON object.

Appendix 4: Research Question Generation Inference

You are provided with a list of paper titles and you are tasked to find research questions that might be answered developing a new theoretical model. Return a JSON-object with an array of strings, each representing a potential research question in the following format: {"research_questions": string[]}. Return only a JSON array of strings, no additional text.

[Source document titles]

Now, provide an array of 5 potential research questions.

Appendix 5: Brainstorming Applicable Theories Inference

Your task is to brainstorm theoretical models from existing literature that could be applicable to the research findings. Each theory should be well-defined and should relate to one or more aggregate dimensions. The output should be a JSON-object with an array following this schema:

{"theories": {"theory": string, "description": string, "relatedDimensions": string[], "possibleResearchQuestions": string[]}[]}

Our research aims to understand specific phenomena within a given context. We have identified multiple aggregate dimensions and second-order codes that emerged from our data. Could you suggest theories that could help explain these dimensions and codes? The aggregate dimensions and codes are as follows: [Aggregate dimensions and corresponding second-order codes]

Appendix 6: Developing Concept Tuples Inference

Your task is to hypothesize which concepts could be related to each other. Return a JSON-object with an array of tuple arrays, where each tuple array represents a possible relationship between two concepts. The output should be a JSON-formatted array following this schema: {"tuples": [[string, string], [string, string], …]}. E.g. {"tuples": [["Knowledge Management", "Organizational Performance"]]}. This allows us to in the next step research the relationship between the concepts in the literature.

Our research aims to understand specific phenomena within a given context. We have identified multiple aggregate dimensions and second-order codes that emerged from our data.

[Aggregate dimensions and corresponding second-order codes]

Now, hypothesize which concepts could be related to each other and return only the JSON-formatted array of 10 - 20 tuples.

Appendix 7: Interrelationship Summarization Inference

Your task is to summarize the interrelationship between [Concept 1] and [Concept 2] in one short sentence. If evidence, include information about correlation or causation, direct, mediated or conditional interaction, static or dynamic relationship, feedback loops, uni- or bi-directional, strong or weak.

[Relevant paragraphs]

Now, provide a summary in one short sentence.

A growth philosophy focused on high growth and a liquidity event aligns with an exit strategy predicated on achieving rapid scaling and value maximization for a timely IPO or acquisition.

Appendix 8: Model Construction Inference

You are a qualitative researcher tasked with constructing a theoretical model from existing literature that could be applicable to the research findings. The model should be well-defined and should relate to one or more aggregate dimensions. It should be novel and original. You can build on existing theories, however, you should introduce new ideas. Emphasize the relationships between the dimensions and the model. Explain how the relationships might be causal or correlational, be clear on the narrative. You are non-conversational and should not respond to the user, but give a general description of model. Give a name to the model.

Previous model: [Previously developed model (if available)]

Critique: [Critique (if available)]

Relevant existing theories: [Relevant existing theories]

The aggregate dimensions and codes are as follows: [Aggregate Dimensions and Second Order Codes]

Now, construct an extensive, comprehensive, new, theoretical model.

The Integrated Entrepreneurial Dynamics Model (IEDM) is a theoretical construct formulated to address the multifaceted and dynamic interactions between individual entrepreneurship dimensions and the collective strategic trajectory of a venture. The IEDM synthesizes concepts from the Adaptive Synergistic Influence Model (ASIM) and extends them by introducing additional dimensions and deepening the narrative on interactions. […]

Appendix 9: Model Name Extraction Inference

You extract theoretical model names. If none given, invent an original one. You only reply with the name, nothing else.

[Model Description]

Now, return the model name

Integrated Entrepreneurial Dynamics Model (IEDM)

Appendix 10: Visualization Inference

You are a qualitative researcher tasked with visualizing a theoretical model with MermaidJS. Example:

flowchart TD

%% Nodes A[Organizational

Culture<br>’evidence

1’<br>’evidence2’]

B[Leadership Style]

C[Employee Satisfaction]

D[Employee Productivity]

E[Customer Satisfaction]

F[Financial Performance]

%% Relationships

B ==>|Directly

Influences<br>’evidence

A -.->|Moderates| C

D –>|Impacts| E

C -.->|Partially

Mediates| F

As we have seen in above diagram, ==> is used to indicate a strong direct influence, –> is used to indicate a weaker influence, -.-> is used to indicate a moderating relationship, and — is used to indicate a correlation.

Evidence can be cited by adding a line break and then the evidence in single quotes. Use first-order codes or second-order codes as evidence only, preferably not as their own nodes.

Now, given a model description, you should generate a MermaidJS diagram like the one above, showing the interrelationship between different concepts. Keep it simple and effective. You are non-conversational and should not respond to the user, only return the MermaidJS code, nothing else.

First-order codes: [First-order codes]

Appendix 11: Critiquing Inference

You are a qualitative researcher tasked with critiquing a theoretical model. Offer your comments on novelty, conciseness, clarity and theoretical insight and brainstorm potential new patterns to discover in the data. You are non-conversational and should not respond to the user, only return the critique, nothing else.

First order codes: [First-order codes]

[Interrelationships]

[Model Name]

Now, return your critique

Critique of the Adaptive Synergistic Influence Model (ASIM):

Appendix 12: Survey - Demographics

Other: PhD student, machine learning engineer, Programmer

Appendix 13: Survey - What types of qualitative data do you usually work with?

"Interviews

"- interviews

- case studies

- background information

- expert opinions

"I usually work with metaanalysis, sometimes with surveys."

I don’t generally work with qualitative data.

case studies

Survey data

"Facts, data and figures relating to company key figures, historical data on key economic indicators such as GDP, inflation and unemployment figures. Furthermore, research into historical share, fund and price indices performance and price development."

"Interview transcripts, audio recordings of interviews"

Speech and text

"documents, videos, images"

"Customer Feedback and Interviews, Expert Opinions and Consultations, Internal Documents and Reports"

"Interviews, surveys and observations"

"academic papers from databases like EBSCO that include graphs and tables summarising the results of their study. "

"Company data such as internal documentations, and website data."

"I usually work with documents and observational studies.

Appendix 14: Survey - What methods or tools do you use for qualitative data analysis? How do you make sense out of your collected qualitative data?

"Thematic analysis

Until now I don’t work with qualitative data analysis tools

"I use web databases, as well as tools like microsoft forms or google forms."

"Qualitative methods, testing qualitative data with quantitative research tools"

"mostly I use literatire review and case law analysis "

"I read them, intuition"

"EBSCO, EMERALD, Statista"

"thematic analysis - reading through, adding codes, developing codes into themes, rereading, seeing if there is a fit, maybe starting again"

"I use NLP techniques like Sentiment Analysis, Named Entity Recognition and Topic Modeling"

"python library: cv2, pandas, PLT

I make sense of my data using statistics and "

"Content Analysis, data categorisation, knowledge discovery"

"A voice recorder on the phone is used for recording the interviews, which then need to be transcribed. There is ATLAS.ti which is great for thematic coding. So far, google docs or a simple notebook provides the workspace for notes "

"most of the time I perform a literature review using qualitative papers to understand the research up to that point and find gaps in research. other than that I have done empirical research on a dataset using the pandas library in Python3. "

"GPT, Context Retreival (such as langchain tools), vectorization and vector databases."

I usually use ATLAS.ti and it provides me visual representation of needed data

Appendix 15: Survey - Do you create theoretical models to describe your qualitative data? If so, what methods or tools do you use for theory development?

"Do you create theoretical models to describe your qualitative data? If so, what methods or tools do you use for theory development?"

I don’t remember the models I used as I no longer do social science research not really as of now

I sometimes use legal theories but would not say I create a theoretical model per se

"no, purely empirical"

"not really, I mean I would come up with themes, I don’t think that counts as a theoretical model?"

"Grounded Theory Methodology, Conceptual Framework Developmen"

"In a way, I interpret this as creating a mind map or flow chart to represent the data, perhaps that created by the themes. I use Canva to fit it to the topic of the paper. "

"I mainly look at regression models that try to quantify the correlation between different variables. various python libraries like pandas, numpy, matplotlib and seaborn aid in that process. "

I have never used a model in my academic work before

Appendix 16: Survey - If any, which AI tools do you use when conducting research?

"If any, which AI tools do you use when conducting research?"

I stopped SS research before the rise of AI tools

"Manly ChatGPT, but due to high error rates and mistakes in the outcome you have to check every single fact - so I prefer traditional ways of research "

"I seldom ever use AI, though occasionally I use ChatGPT for personal projects brainstorming."

I haven’t tried to use it for research yet.

chatGPT but only rarely

"chatgpt, sometimes forecasting tools and voice transcription" None

"Fairseq, Huggingface, Pytorch"

"Machine Learning Platforms:

TensorFlow, PyTorch, or scikit-learn

RapidMiner or KNIME,

NLTK, SpaCy, or Gensim"

"I use ChatGPT to generate ideas or make it easier to narrow my search by finding out what is already out there. "

"I started using chatGPT to speed up the coding process in Python when i am performing my own data analysis. "

"GPT, BERT"

Appendix 17: Survey - Which dataset are you using?

Your own dataset: Health Effects of Cocoa, looked something up, An Interview extract on Fear of Confrontation, just performed a search for litarature in search barbar

Appendix 18: Survey - How easy was it to learn AcademiaOS?

Appendix 19: Survey - Did you require assistance to start using AcademiaOS? If yes, what kind of assistance?

"Did you require assistance to start using AcademiaOS? If yes, what kind of assistance?"

"No, but you should mention that the user can also upload non-pdf files (I was trying to batch-convert the 45 AI policies to pdf, but I figured that I’d still try to upload the .txt and it worked)"

Slight assistance by a more knowledgable other.

It would be nice to have tips that pop up within the website/ explanations of what each button does/ a tutorial when you first open the website

without the youtube video it is a little bit hard to understand what I should do in each step and how I can use the tool

Just an error code for not accepting the format of my pdfs

The video was enough to understand the workings.

Appendix 20: Survey - I have found and used the option to search for academic papers.

Appendix 21: Survey - I have found and used the option to upload my own sources.

Appendix 22: Survey - I have found and used the option for "coding" sources.

Appendix 23: Survey - I have found and used the option to develop a theory.

Appendix 25: Survey - Describe any difficulties you had navigating the platform.

"submit pdf user prompt doesn’t mention other formats. more user input description everywhere would be nice (ie ""search for papers here)"

"In the mobile version I couldn’t see some buttons " Hard to navigate

I couldn’t find the coding help function

"the insert key thing was rather hidden, I’d like to have it in a more central, permanently visisble place - I suspect thats going to be the main source of error why people can#t use it."

I had no difficulties

"about the code part, didnt really understand how to use it "

"Just that there was an error in using any of the pdfs, personal pdfs or from the site"

I do not know how to use the coding and moddeling modules without watching the video. also i got a bunch of json object not supported errors when trying to use coding.

"I keep getting 400 Invalid parameter: ’response_format’ of type ’json_object’ is not supported with this model.. I dont understand what I did wrong, so maybe the UI design can support the user better to understand how to enter data or entries that doesnt cause that error."

I belive there were ocassions when the platoform was loading too slowly and i had to re start it several times.

Appendix 26: Survey - How would you improve the user-interface and experience of AcademiaOS?

How would you improve the user-interface and experience of AcademiaOS?

more user testing to make it as simple as possible. Happy to help […]

"No idea for that "

"Make it more user-friendly, less technical"

"I would be nice to have filters for finding papers (ex year of publication), if it is there then sorry for not finding it"

"add examples of what one could write in the text boxes, not just descriptoins. I left them empty bc my brain wasn#t creative enough. also you could imporve error handling, just wrap a try catch around the enitre thing and if it errs, rerun it automatically? Dumb users get stuck if it crashes, even if you tell them to just hit rerun"

I think it’s pretty good the way it is! I like the dark mode

I would recommend to have a link in the landing page which show/explain how to use the tool

"I think it is already an amazing and quick way of organising qualitative data. You provided a youtube video here, perhaps an instructions page on the site?"

"i recon i need to watch the video to understand how to properly use it. but i would also like to be able to combine different searches or datasets in one coding tab because i dont always find al my sourses at once. . " Described on previous answer.

Improve the speed of processing

Appendix 28: Survey - Looking at the 3-step coding of the qualitative data, how would the system-output compare to potential manual coding?

Appendix 29: Survey - Describe any instances where the system-produced codes did not meet your expectations.

"Honestly, it would be too long for me to check manual vs AI-driven but the 100x speed of the AI option is an asset in itself, can put you in the right direction fast"

"English-German "

I put in a research question whose answer depended only partly on the sources and partly on theory in the academic literature and it was not able to catch that and make codes relevant to the research question. Still for a general summary of the sources the codes seem pretty good (even though I did not read the sources)

"I was getting 400 We could not parse the JSON body of your request. (HINT: This likely means you aren’t using your HTTP library correctly. The OpenAI API expects a JSON payload,"

Some papers did not directly apply to my research questions but had the key word that i searched for

Appendix 30: Survey - How effective is AcademiaOS in augmenting the coding process for qualitative data?

Appendix 31: Survey - How satisfied are you with the theory development process?

Appendix 32: Survey - Looking at the produced theory, how would the system-output compare to manual theory development?

Appendix 33: Survey - Describe any instances where the system-produced steps in theory development did not meet your expectations.

Once again difficult to say without having my own coding done

"It was kind of complex, and I often didn’t really get where it was going with the theory."

"Again, the theory seems to cover the content of the sources pretty generally but is not really about the research question I posed."

"I think two theories generated where quite similar, but that also means it provides me with options as to what theory I prefer"

I have never coded qualitiative data before so i dont have expectations

Appendix 34: Survey: How effective is AcademiaOS in augmenting the theory development process?

Appendix 35: Survey - AcademiaOS would impact my qualitative research process?

Appendix 36: Survey - How would the use of AcademiaOS change the way you perform qualitative research?

"it will speed up the research "

Multiple draft iterations to inspire/shortcut the manual process

"Much faster "

Making it easier for me to do my research especially in hours where I cannot concentrate that much

It would make the coding and theory production much faster

It would be very useful for iterating quickly and exploring different documents

"It will urge many scientists to increase their throughput and let the computers do the analysis. I also carries the potential to mitigate the information retrieval and retention of humans. "

It feels like cheating to me…I would not feel comfortable using it.

I would use it to rapidly prototye theories i could be building

"I would still want to read my sources first, and get an impression, maybe even do some coding. Then I could use the platform to compare and maybe find things I missed before. I think the theories feature is also really cool for inspiration."

I don’t generally do qualitative research (basically never) so take my answers with a grain of salt maybe

"I believe it would help me to link concepts easier "

Appendix 37: Survey - How could AcademiaOS change the output of your qualitative research?

Providing a guidance It would if I did more qualitative research

"more varied and tested theories, better theories through more input ideas, more feedback"

"I think I have too much pride to use a fully AI generated model as the output for my research, it would make me feel too replaceable. I also don’t quite trust the quality (mostly from experience with ChatGPT), I would always want to check it for what it misses. So it might change my output somewhat, if it gave me new ideas but not replace what I would usually do. Hopefully."

"it will make it better structured "

I could use the models created as part of a clear visualisation for my papers

"It will make the throughput of scientist much higher, while helping the science to be more reproducible."

It gives me paper suggestions faster hence it would give me more time to do my research and search for the best possible sources

Appendix 38: Survey - What limitations do you see in using AcademiaOS?

Currently the lack of filters for the papers.

"As I said earlier, it doesn’t seem to be able to make sense of a somewhat more specific research question but rather work from the sources up, generating a kind of summary of everything the sources provide. This also indicates that it might fail to generate very latent codes."

Treating other modalities like speech

processing time

"I fear it may cause people to not properly look at the nuances of their interviews or papers. "

"Currently it is using a single AI model, which makes it difficult to rule out its biases. In the future consortium based agents can help building less biased applications."

That sometimes the Platform just links the keyword but fails to link it within the concept that im looking for.

Appendix 39: Survey - I feel excited about the possibilities that AcademiaOS provides.

Appendix 40: Survey - I fear being replaced by AI.

Appendix 41: Survey - AcademiaOS allows me to ground my research on more qualitative data.

Appendix 42: Survey - AcademiaOS allows me to conduct research faster.

Appendix 43: Survey - AcademiaOS allows me to find more impactful results.

Appendix 44: Survey - AcademiaOS allows me to find more unexpected results.

Appendix 45: Survey - How likely are you to continue using AcademiaOS for your research?

Appendix 46: Survey - How likely is it that you recommend AcademiaOS to your friends?

Appendix 47: Survey - I am excited about future versions of AcademiaOS.

Appendix 48: Survey - Any final comments?

"The survey might be difficult to get good answers from because it partly relies on the user comparing their coding work with the AI’s, which would take at least an hour (and is conditional on the participant having experience in qualitative research)"

Much needed AI

"I’m concerned about AI regulations in education - this is a big reason I would not use the platform. Feels a bit like cheating, and I wonder if the university would see it that way too and if that would have consequences. But in any case, I think the whole thing is really impressive."

nice tool just need some improvement: how to use intro and some bugs fixing

"Great Tool! "

"I have never preformed qualitative data analisis which disqualifies me from being able to compare the workflow using academiOS with a prior one. also, I might have mistaken qualitative for quantitative at the beginning of this survey but there is no back button so i cannot go back. "

I will share this with my old research groups.

"I am excited for the future of this platform, you did a great job :)"

Appendix 49: Coding University Policies

Appendix 50: Applicable Theories for University Policies

Appendix 51: Interrelationships for University Policies

Appendix 52: First Iteration Model for University Policies

Academia-OS-generated model text:

“Given the complexities surrounding the adoption of AI technologies in education and the necessity to preserve academic integrity, I present the Holistic Framework for Integrity and Adaptation in AI-Enhanced Education (HIAIEE). This theoretical model explicates the multidimensional relationship between educational policy, technological integration, pedagogical adaptation, assessment practices, ethical considerations, and the dynamics of student and faculty interaction within the context of AI enhancements in an educational setting, interfacing with institutional and cultural values. ### Model Components: **1. Educational Policy and Regulation Dimension (EPRD)** This dimension encompasses the creation and adjustment of policies and regulations to ensure academic integrity in the face of AI advancements. **2. Technological Integration and Response Dimension (TIRD)** This axis represents the approaches to assimilating AI technologies in educational practices, and the responses that are required to maintain academic standards. **3. Teaching and Learning Adaptation Dimension (TLAD)** This dimension explores how pedagogical strategies and methodologies must evolve to leverage AI advancements while promoting authentic learning experiences. **4. Assessment and Academic Integrity Dimension (AAID)** Focuses on the design and implementation of assessment strategies that align with the reality of AI tools being available to students, ensuring the preservation of academic integrity. **5. Ethical and Privacy Considerations Dimension (EPCD)** This domain addresses concerns related to ethics, privacy, and intellectual property that arise from the use of AI in education. **6. Student and Faculty Dynamics Dimension (SFDD)** Investigates the evolution of relationships and roles between educators and learners within an AI-incorporated educational context. **7. Institutional and Cultural Considerations Dimension (ICCD)** Examines how institutional practices and cultural attitudes influence and are influenced by the integration of AI within academic settings. ### Model Dynamics: In the HIAIEE model, the dimensions are not isolated entities but are interlinked, each impacting and being affected by the others: - **EPRD ←→ TIRD**: As AI tools are integrated, policies must be regularly updated to reflect new realities and capabilities. A feedback loop is necessary, where policy informs technology use and technology development informs policy adjustments. - **EPRD ←→ TLAD**: Pedagogical adaptations are often a response to the constraints and affordances of policy changes concerning AI utilization. - **EPRD ←→ SFDD**: Policy adjustments require a deep understanding of the existing and emergent dynamics between students and faculty to be effectively implemented and enforced. - **TLAD ←→ AAID**: Teaching methodologies and assessment designs are reciprocally influenced; innovative pedagogical approaches necessitate novel assessment methods that AI tools are less likely to compromise. - **AAID ←→ SFDD**: The means through which academic achievement is assessed shapes the interactions between students and faculty, especially around expectations of integrity and the perception of fairness. - **EPCD → All dimensions**: Ethical and privacy considerations hold a guiding role, influencing every other dimension. Policy, technology integration, teaching practices, assessments, and dynamics all must adhere to ethical standards. - **ICCD ←→ All dimensions**: Cultural and institutional ethos serve as the backdrop against which all adaptations take place, and they are also conversely reshaped by changes within each dimension. ### Causal and Correlational Relationships: In the HIAIEE model, causal relationships suggest that changes in one dimension directly bring about changes in another. For instance, policy reform (EPRD) may cause a change in teaching adaptations (TLAD). Correlational relationships imply that variations in dimensions are related but not causative; rather, they tend to evolve in response to common underlying factors, such as shifts in academic culture (ICCD). ### Implementation: Implementing HIAIEE necessitates a multi-stakeholder approach, involving policymakers, technologists, educators, and students to co-create solutions that are robust, adaptable, ethical, and aligned with the fundamental goals of education. It requires iterative development and ongoing dialogue to remain effective as AI technologies continue to evolve. Given the user’s remarks, the HIAIEE model provides an actionable framework for educational institutions to navigate the complexities of adapting academic integrity policies in the age of AI writing tools, ensuring a well-rounded response that integrates technology effectively while maintaining the core values of education.”

Appendix 53: Critique for First Iteration Model for University Policies

As there is no specific theoretical model provided for critique, I will offer general guidance on how to assess a theoretical model in qualitative research: 1. **Novelty**: A novel theoretical model should contribute new perspectives or ways of understanding phenomena. In assessing novelty, consider whether the model offers a unique integration of concepts or identifies previously unexplored relationships between variables. Also, consider if it fills a gap in the literature, challenges existing paradigms, or proposes new hypotheses for investigation. 2. **Conciseness**: Theoretical models should be as simple as necessary but as complex as needed to explain the phenomena in question. Check for superfluous elements or overly convoluted relationships that can be streamlined. Conciseness also involves ensuring that each aspect of the model is essential and that the model is not redundant with existing theories unless it significantly improves on or clarifies them. 3. **Clarity**: A clear theoretical model is one that can be easily understood and applied by other researchers. Clarity involves precise definitions of the model’s components, understandable logic connecting the components, and clear visualization if a graphical representation is used. The model should be free of jargon, or if specialized terms are necessary, they should be well-defined. 4. **Theoretical Insight**: Evaluate the model for its depth of insight into the research problem. A model with strong theoretical insight will not only describe or classify elements but will explain processes, predict outcomes, and provide a framework for understanding complex relationships. It should have the potential to guide future research, suggesting new questions or methods of investigation. When brainstorming potential new patterns to discover in the data, the following steps might be useful: - Look for inconsistencies or contradictions in the data that do not fit the existing model. These might indicate areas where the model needs to be expanded or revised. - Analyze outliers or exceptional cases to understand why they do not conform to the expected patterns. These cases can sometimes lead to the identification of new variables or relationships. - Use alternative analytical lenses or perspectives to re-interpret the data. This might involve interdisciplinary approaches or the application of theories from different fields. - Conduct comparative analysis across different groups, settings, or time periods to identify if and how patterns may vary, which can lead to new dimensions being incorporated into the model. - Employ a grounded theory approach, generating theoretical insights from the data through iterative coding and analysis, allowing new patterns and relationships to emerge organically. Remember that the ultimate goal of a theoretical model is to advance understanding, guide research, and offer meaningful explanations that can be empirically tested and validated through qualitative or quantitative methods.

Appendix 54: Second Iteration Model for University Policies

Model Name: Integrated Education Adaptation Framework for AI Readiness (IEAFAR) The Integrated Education Adaptation Framework for AI Readiness (IEAFAR) is a theoretical model designed to navigate the multifaceted challenges and opportunities posed by the integration of artificial intelligence (AI) in educational contexts. It aims to provide a comprehensive guide for educators, policymakers, and institutions to adapt efficiently and ethically to the disruptive potential of AI technologies like AI writing tools, while ensuring academic integrity and enhancing the educational experience. ### Model Components: **1. AI Integration and Educational Dynamics (AI-ED)** This dimension captures the bidirectional influence between AI technology integration and the evolving dynamics in education, including pedagogy, student-teacher interactions, and curriculum development. **2. Adaptive Compliance and Policy Evolution (ACPE)** This aspect examines how educational policies and regulations must adapt to the challenges posed by AI, focusing on academic integrity, legal implications, and institutional responsibilities. **3. Academic and Instructional Resilience (AIR)** This dimension depicts the institutional and faculty’s ability to maintain effectiveness and recover from the disruption caused by AI, through innovative teaching methods, assessment practices, and resource allocation. **4. AI-Driven Educational Innovation (ADEI)** This represents the transformative potential of AI in creating new educational paradigms, including personalized learning, adaptive resources, and new forms of student engagement. **5. Ethical, Legal, and Societal Harmony (ELSH)** This dimension emphasizes the alignment of AI integration with ethical standards, legal requirements, and societal values, ensuring that AI serves to enhance rather than detract from human welfare in education. **6. Collaborative Stakeholder Engagement (CSE)** This axis highlights the collective participation of all stakeholders—students, educators, technologists, policymakers, and the society at large—in the shaping and implementation of AI in education. ### Model Dynamics: The IEAFAR model proposes a series of interconnected relationships stemming from the core premise that educational adaptation to AI is a holistic and iterative process: - **AI-ED ACPE**: Innovation in AI necessitates adaptive policies and regulation that promote compliance and navigate the balance between empowerment and control within educational institutions. - **AI-ED AIR**: Changes in educational dynamics due to AI influence pedagogical resilience, demanding that institutions be agile and resourceful in updating instructional methods. - **AI-ED ADEI**: Integration of AI technologies should be leveraged for educational innovation, expanding the horizons of what is possible in teaching and learning. - **ACPE → ELSH**: Policies relating to AI must be crafted with a keen awareness of ethical, legal, and societal considerations, ensuring harmonious integration. - **AIR ELSH**: The level of instructional resilience correlates with the adherence to ethical and legal standards, ensuring that innovation does not outpace the institution’s duty to act responsibly. - **ADEI → CSE**: New paradigms of education emerging from AI need collaborative input and acceptance from all stakeholders, fueling a cycle of engagement and feedback. - **CSE → All dimensions**: Stakeholder engagement acts as a critical force across all dimensions, influencing and being influenced by changes in integration, policy, innovation, and ethics. ### Causal and Correlational Relationships: In the IEAFAR model, causal relationships are understood as direct effects that one component has on another (e.g., ACPE directly shaping ADEI). Correlational relationships imply a mutual evolution where changes in dimensions reflect and resonate with each other without a clear line of causality (e.g., AIR and AI-ED develop in tandem as teaching methods adapt to new AI technologies). ### Implementation: Effective implementation of IEAFAR calls for structured collaboration and regular dialogue among stakeholders. It would involve a commitment to continuous learning, flexibility in adapting to new information and technologies, and a willingness to recalibrate both policies and practices within the ethical, legal, and societal framework. IEAFAR elucidates the complexity of educational adaptation to AI, providing an architecture for systematically addressing the intersection between technological advancements and educational imperatives. It supports a dynamic relationship between innovation and tradition, proposing that proactive adaptation and integrity form the twin pillars of a forward-thinking educational institution poised for the AI era.

Appendix 55: Coding of How I Built This

Appendix 56: Model of How I Built This

Appendix 57: First-Order Coding of Cardiovascular Health Effects of Alcohol

Appendix 58: First Iteration Model for Cardiovascular Health Effects of Alcohol

Model Name: **The Dynamic Alcohol Impact Reconstruction Model (DAIRM)** Model Description: The Dynamic Alcohol Impact Reconstruction Model (DAIRM) is an innovative theoretical framework that seeks to elucidate and predict the multifactorial impact of alcohol consumption on individual and public health by integrating and extending upon existing theoretical constructs while introducing novel aggregates. The model distinguishes itself by its dynamism, acknowledging not only static factors but also changes over time and in varying contexts. It highlights the complexity of the interactions between personal, social, biological, and policy-driven factors, offering a nuanced and adaptable template for exploring the vast spectrum of alcohol-related health outcomes. Model Structure: 1. Central Dimension: Individual Impact Nexus - Serves as the convergence point for various direct influences and outcomes of alcohol consumption at the individual level. This includes both acute and chronic health effects, personal behavior patterns, and psychological states. 2. Aggregate Dimensions: - Sociocultural Ecosystem * Encompasses societal norms, cultural beliefs and practices, legal frameworks, and policy initiatives, highlighting their correlation and causal influence on drinking behaviors and vice versa. - Biological Embedding Mechanism * Represents the physiological and neurochemical processes affected by alcohol, detailing how genetic predispositions and metabolic changes can causally impact health. - Behavioral Formation Grid * Maps out how cognitive, emotional, and experiential factors interact to form alcohol consumption behaviors, acknowledging the correlational and occasionally causal relationships between beliefs, intentions, and actions. - Temporal Dynamics Pathway * Introduces the element of time, considering short-term versus long-term effects, life course variations, and the evolving nature of health impacts in relation to shifting patterns of alcohol use. Relationships and Narratives: 1. Sociocultural Influence → Behavioral Formation Grid (Correlational and Causal) - Sociocultural norms and policies influence individuals’ beliefs about and engagement with alcohol, which in turn shape consumption behaviors. This relationship can be bidirectional as changes in behavior may feedback into sociocultural evolution. 2. Biological Embedding Mechanism → Individual Impact Nexus (Causal) - The biological effects of alcohol, including molecular and cellular changes, lead directly to various health outcomes. How one’s body processes and is affected by alcohol is also moderated by genetics, highlighting a complex causal network of biological responses. 3. Behavioral Formation Grid → Individual Impact Nexus (Correlational) - Personal beliefs, decision-making processes, and subsequent behavior patterns correlate with the range of health outcomes experienced by individuals, suggesting that cognitive and emotional factors play significant roles in shaping behaviors that impact health. 4. Sociocultural Ecosystem ↔ ↔ \leftrightarrow ↔ Temporal Dynamics Pathway (Correlational) - Social norms, policies, and cultural contexts evolve over time, and their impact on health behaviors and outcomes may vary accordingly. This pathway draws attention to the historical and prospective trends that influence drinking habits and their repercussions. 5. Temporal Dynamics Pathway → Individual Impact Nexus (Causal and Correlational) - The effects of alcohol on health vary over time, indicating a temporal dimension where both acute reactions and long-term consequences come into play, illustrating the importance of life course and temporal variations in health impacts. 6. Biological Embedding Mechanism ↔ ↔ \leftrightarrow ↔ Behavioral Formation Grid (Correlational) - Underlying biological factors may influence cognitive and behavioral responses to alcohol (e.g., tolerance, cravings), suggesting a bidirectional correlation where biology impacts behavior and repeated behaviors can reinforce biological responses. 7. Sociocultural Ecosystem ↔ ↔ \leftrightarrow ↔ Biological Embedding Mechanism (Correlational) - Cultural and societal views on alcohol can influence policies that may indirectly affect biological research agendas, funding, and health education, which in turn may inform policy. This indicates a correlational relationship involving feedback loops. Model Applications: The DAIRM is intended to: - Support multi-dimensional public health initiatives by fostering a comprehensive understanding of alcohol’s diverse impacts. - Direct future interdisciplinary research aiming to explore and elucidate the complex factors influencing individual and collective health outcomes related to alcohol. - Facilitate the development of custom-tailored clinical interventions and societal policies crafted to address the specific needs and influencers of distinct populations. - Provide a platform for examining and tracking the shifting paradigms of alcohol-related behaviors as influenced by emerging trends, technologies, and global events. Model Innovation: DAIRM’s originality arises from the inclusion of novel elements like the Temporal Dynamics Pathway, which incorporates longitudinal changes and shifts in behavior and impact, acknowledging the fluidity of alcohol consumption patterns. Additionally, the integration of diverse dimensions into a unified model underscores the intricate causal and correlational relationships, advancing beyond static frameworks that fail to account for interactions over time and context-specific factors. This holistic and dynamic approach not only supplements but transcends traditional theoretical constructs in the realm of alcohol research.

Appendix 59: Critique on First Iteration Model for Cardiovascular Health Effects of Alcohol

Critique of the Integrated Health Impacts of Alcohol Model (IHIA Model): Novelty: The IHIA Model’s strength lies in its attempt to create a holistic framework that encompasses various dimensions of alcohol’s impact on health. Its innovative approach to integrating biological, psychological, social, and policy-related factors is commendable as it attempts to provide a comprehensive understanding beyond traditional models. The consideration of both causal and correlational relationships connects different research areas and could lead to deeper insights for public health interventions. Conciseness: The IHIA Model, while comprehensive, might struggle with conciseness due to its vast scope. The model may become complex when trying to simultaneously account for numerous factors across different domains. This complexity could challenge the clarity with which the model can be communicated to stakeholders and implemented in practice. Clarity: The fundamental concepts and domains of the IHIA Model are well-defined, offering a clear platform for understanding the multi-faceted impacts of alcohol consumption. However, the clarity of interaction between domains—particularly the ways in which all domains interact reciprocally—may need further elucidation to prevent oversimplification of complex relationships. Theoretical Insight: The IHIA Model provides significant theoretical insight by recognizing the dynamic interplay between alcohol consumption patterns and a broad range of factors affecting health. It encompasses well-known theories and builds upon them, which reinforces the complex nature of health-related behaviors and outcomes. Brainstorming Potential New Patterns: Considering the IHIA Model’s potential in discerning complex patterns, future research may consider investigating: - The interaction effects of combining different drinking patterns with various types of alcoholic beverages on long-term health outcomes. - How socio-cultural shifts, like changing gender roles or economic fluctuations, influence alcohol consumption behaviors and subsequent health impacts. - The role of digital social platforms in influencing drinking habits, especially among younger demographics, and how this relates to psychological and physical health outcomes. - The impact of personalized genetics and precision medicine on the efficacy of public health policies designed to mitigate the harms of alcohol. - Cross-national comparative studies to explore how different legal and cultural environments shape alcohol consumption patterns and health outcomes, potentially uncovering new variables for the model. In summary, the model excels in its integrative and innovative nature but may face challenges in maintaining conciseness and clarity due to its complexity. Further development should focus on elucidating the multi-directional interactions of the domains and exploring new patterns that may emerge from data, particularly in the rapidly changing social and policy landscapes.

Appendix 60: Second Iteration Model for Cardiovascular Health Effects of Alcohol

Model Name: Dynamic Socio-bio-psychological Model of Alcohol Impact (DSBPAI) Model Description: The Dynamic Socio-bio-psychological Model of Alcohol Impact (DSBPAI) is a theoretical construct designed to synthesize and build upon existing literature to explore the intricate relationships between alcohol consumption and diverse health outcomes. This model explicitly acknowledges the multidimensionality and dynamism of factors at play, categorizing and integrating biological (bio), psychological (psycho), and sociodemographic (socio) influences within a complex, adaptive system. The DSBPAI model conceptualizes the interactions across different levels—individual, social, and policy—and maps out the reciprocal feedback mechanisms that modulate these interactions over time. Model Structure: 1. Individual Well-being Sphere: - The core of the model is individual health and well-being, integrating physical (bio), mental (psycho), and social (socio) health dimensions as dynamic and interrelated. 2. Aggregate Dimensions: - Biochemical Reaction Network * Denotes biological processes including metabolic pathways, genetic predispositions, and physiological responses to alcohol, providing a causal mapping with individual health outcomes. - Psychological Complexity Framework * Captures cognitive, emotional, and behavioral responses to alcohol, incorporating both individual differences and common psychological patterns, facilitating correlational associations and feedback loops with health outcomes. - Socio-Environmental Influence Fabric * Constitutes the spectrum of social, cultural, economic, and policy-related factors that influence and are affected by alcohol consumption, highlighting the correlation and potential for causal relationships on both individual and population health levels. Relationships and Narratives: 1. Biochemical Reaction Network → Individual Well-being Sphere (Causal) - Direct causal biochemical and physiological reactions result from alcohol consumption, affecting health outcomes through discrete, quantifiable biological changes. 2. Psychological Complexity Framework ↔ ↔ \leftrightarrow ↔ Individual Well-being Sphere (Correlational and causal) - Psychological dispositions and experiences influence and are influenced by individual health outcomes, forming a bidirectional relationship where feedback loops are common and causality can be context-dependent. 3. Socio-Environmental Influence Fabric ↔ ↔ \leftrightarrow ↔ Psychological Complexity Framework (Correlational) - Socio-environmental factors correlate with psychological approaches to alcohol use and vice versa, reflecting the influence of society on individual mentality and behavior towards alcohol. 4. Socio-Environmental Influence Fabric → Biochemical Reaction Network (Causal) - The social dimension, through policy impacts and environmental components, impacts biological processes by influencing the patterns and nature of alcohol consumption, which can cause health outcomes. 5. Socio-Environmental Influence Fabric ↔ ↔ \leftrightarrow ↔ Individual Well-being Sphere (Correlational and Causal) - The fabric of socio-environmental influence has a bidirectional relationship with individual health outcomes, whereby it shapes, and is shaped by, the collective health and consumption behaviors of individuals. 6. Psychological Complexity Framework ↔ ↔ \leftrightarrow ↔ Biochemical Reaction Network (Correlational) - The interplay between psychology and biology acknowledges the psychosomatic nature of health, where psychological states can correlate with and sometimes affect biochemical reactions to alcohol. 7. Biochemical Reaction Network ↔ ↔ \leftrightarrow ↔ Socio-Environmental Influence Fabric (Causal) - Emerging evidence suggests biological factors can inspire shifts in the socio-environmental domain, as understanding of health risks/benefits of alcohol influences social norms and policies. Model Applications: The DSBPAI model is designed to: - Act as a heuristic tool for researchers and clinicians to identify and analyze the feedback loops between individual behavior and broader societal structures in the context of alcohol consumption and health outcomes. - Inform health policies and public health strategies by identifying leverage points within the socio-bio-psychological nexus where interventions could be most effective. - Guide educational campaigns to tailor messages to diverse audiences, acknowledging the complex interactions between individual, societal, and biological components related to alcohol. - Provide a framework for the development of predictive models for public health outcomes related to alcohol by integrating individual and public health data across the biological, psychological, and social domains. Model Innovation: The DSBPAI model introduces the following original components: - Dynamic Feedback Systems: The model adopts systems thinking to demonstrate how feedback loops dynamically modulate the relationships between consumption, psychology, biology, and social context. - Scalable Modularity: Designing the components as modules within a larger system allows for the model to be expanded or focused, depending on the level of analysis, from molecular to societal. - Contextual Health Matrix: This matrix integrates genetic, lifestyle, and environmental health determinants to offer nuanced insights into population-specific alcohol health impacts. The DSBPAI model thus integrates and advances existing knowledge into a comprehensive, dynamic, and multidimensional framework, acknowledging the complex realities of alcohol’s impact on health and society. It provides a cohesive narrative that can evolve and adapt to new data, offering a sophisticated, systemic understanding of the alcohol-health nexus.

Appendix 61: Temperature Test 0 Outcome

Model Name: The Dynamic Synergy Model (DSM) The Dynamic Synergy Model (DSM) is a theoretical framework designed to elucidate the complex interplay between various aggregate dimensions that influence and drive organizational success and sustainability. The DSM posits that the interrelationships between these dimensions are not merely additive but synergistic, leading to emergent properties that can significantly enhance an organization’s performance and resilience. The DSM is composed of eight core aggregate dimensions: 1. Organizational Growth 2. Professional Advancement 3. Financial Strategy 4. Sustainability Initiatives 5. Technological Integration 6. Marketing Effectiveness 7. Operational Excellence 8. Community Relations Each dimension is further broken down into specific codes that represent the operational elements within that dimension. The DSM emphasizes the dynamic and reciprocal relationships between these dimensions, suggesting that changes in one dimension can have cascading effects on others. **Theoretical Constructs and Relationships:** 1. **Organizational Growth and Technological Integration:** - The relationship between these two dimensions is causal. Technological Integration can lead to Innovation and Product Development, which is a sub-code of Organizational Growth. Conversely, the pursuit of Business Development may necessitate advancements in Technology and Digital Transformation. 2. **Professional Advancement and Community Relations:** - This relationship is correlational. Networking and Relationships, a sub-code of Professional Advancement, can enhance Community and Social Engagement. Community Relations can also provide opportunities for Career and Personal Development. 3. **Financial Strategy and Sustainability Initiatives:** - The relationship here is bidirectional and causal. Financial Management and Investment decisions can impact Sustainability and Environmental Impact initiatives, while a focus on sustainability can lead to long-term financial stability and new investment opportunities. 4. **Marketing Effectiveness and Organizational Growth:** - A causal relationship exists where effective Branding and Marketing, as well as Product and Service Delivery, drive Market and Customer Engagement, leading to Organizational Growth. 5. **Operational Excellence and Financial Strategy:** - This is a causal relationship. Addressing Operational Challenges can lead to more efficient Financial Management and Investment, as operational efficiencies often translate into cost savings and improved financial performance. 6. **Technological Integration and Marketing Effectiveness:** - The relationship is causal. Technology and Digital Transformation can enhance Branding and Marketing efforts, making them more effective and efficient. 7. **Sustainability Initiatives and Community Relations:** - This relationship is correlational. Sustainability and Environmental Impact initiatives can improve Community and Social Engagement, as organizations that prioritize sustainability may be viewed more favorably by the community. 8. **Professional Advancement and Technological Integration:** - A causal relationship where Career and Personal Development often requires staying abreast of new technologies, which in turn can drive Technology and Digital Transformation within the organization. **Narrative of the DSM:** The Dynamic Synergy Model suggests that an organization’s ability to thrive in a competitive landscape is contingent upon its capacity to foster synergies between these eight dimensions. The model posits that no single dimension operates in isolation; rather, each dimension is intricately connected to others, creating a complex web of interactions that can either propel an organization forward or hold it back, depending on how well these interactions are managed. For instance, an organization that invests in Technological Integration may find that it not only enhances its Operational Excellence but also amplifies its Marketing Effectiveness. Similarly, a focus on Professional Advancement can lead to improved Organizational Growth through enhanced Networking and Relationships, which in turn can lead to better Community Relations. The DSM encourages organizations to adopt a holistic approach to strategy development, recognizing that the pursuit of excellence in one area can have far-reaching implications across the organization. By understanding and leveraging the dynamic synergies between these dimensions, organizations can create a virtuous cycle of growth, sustainability, and innovation.

Appendix 63: Temperature Test 0.5 Outcome

Model Name: Integrated Framework for Sustainable Market Leadership (IFSML) The Integrated Framework for Sustainable Market Leadership (IFSML) is a theoretical model designed to synthesize the multidimensional aspects of business operations, strategy, and brand management with a clear focus on sustainability, ethical practices, and customer-centric growth. This model is novel in its comprehensive approach to intertwining these dimensions while maintaining a focus on achieving market leadership through sustainable means. **Model Overview:** The IFSML model is structured around four core pillars: Strategic Business Synthesis (SBS), Brand and Customer Integration (BCI), Operational and Sustainability Nexus (OSN), and Networking and Developmental Dynamics (NDD). Each pillar represents an aggregate dimension that encompasses various codes from the provided list. **Pillar 1: Strategic Business Synthesis (SBS)** - Entrepreneurial Journey - Product Innovation and Development - Sustainable Business Practices - Market Disruption and Differentiation - Business Development **Pillar 2: Brand and Customer Integration (BCI)** - Brand and Marketing - Product Identity - Marketing Strategies - Brand Elements - Customer and Market Understanding - Customer Experience and Service - Customer Engagement **Pillar 3: Operational and Sustainability Nexus (OSN)** - Technology and Infrastructure - Production and Manufacturing - Finance and Investment - Environmental Impact and Sustainability - Sustainable Business Practices (cross-listed with SBS) **Pillar 4: Networking and Developmental Dynamics (NDD)** - Networking and Relationships - Personal Development and Career **Model Dynamics:** The IFSML model posits that the pathway to sustainable market leadership is through the strategic alignment and dynamic interaction of these four pillars. The relationships are as follows: 1. **Causal Relationships:** - The SBS influences BCI by determining the overarching strategy that shapes brand identity and marketing initiatives. - The SBS also has a direct impact on OSN, as the strategic choices made by a company will dictate operational priorities and investments in technology and sustainable practices. - NDD affects all other pillars by fostering relationships and personal growth that can lead to strategic partnerships, brand collaborations, and an understanding of evolving market needs. 2. **Correlational Relationships:** - There is a strong correlation between BCI and OSN, as the brand’s promise to customers often requires the operational capacity to deliver on that promise sustainably. - Similarly, the effectiveness of NDD activities may correlate with the strength of a brand (BCI) and the company’s strategic positioning (SBS). **Narrative of the Model:** The IFSML model suggests that a business that effectively integrates its strategic business synthesis with its brand and customer management will be better positioned to achieve market differentiation and leadership. This integration is supported by a robust operational framework that is not only efficient but also committed to sustainability, ensuring that the business practices are in line with environmental and ethical standards. Networking and developmental dynamics serve as a catalyst for growth and innovation, providing the necessary insights and relationships to keep the business agile and responsive to market changes. The emphasis on personal development within NDD ensures that the company’s leadership and workforce are equipped to handle the challenges of a dynamic business environment. The IFSML model is original in its comprehensive approach to business leadership, combining strategy, branding, operations, sustainability, and networking in a cohesive framework. It provides a roadmap for businesses seeking to achieve and maintain market leadership by prioritizing sustainability and ethical practices without compromising on customer engagement and operational excellence.

Appendix 64: Temperature Test 1 Outcome

Model Name: The Integrated Framework for Sustained Entrepreneurial Advancement (IFSEA) The Integrated Framework for Sustained Entrepreneurial Advancement (IFSEA) is a theoretical model designed to encapsulate key aggregate dimensions relevant to the lifecycle of entrepreneurial ventures from inception through various stages of growth. This model seeks to establish relationships and potential causal pathways between innovation, strategy, marketing, entrepreneurial experience, financial management, consumer relations, and sustainability. Each of these dimensions represents a vital component of a thriving business ecosystem. Theoretical Constructs: 1. Innovation Engine - Combines "Innovation and Product Development" with elements of "Strategic Business Insights" to drive the creation of unique products and the forming of strategies to maintain a competitive edge. 2. Brand Orbit - Entails "Marketing and Branding" and integrates "Consumer Relations and Outreach" to resonate with consumer experiences and engagement, fostering brand loyalty and market identity. 3. Entrepreneurial Odyssey - Encompasses "Entrepreneurial Experience" and infuses personal growth narratives within the business development process. 4. Fiscal Architecture - Includes "Financial Management and Growth" and is concerned with the financial scaffolding that supports business operations and expansion. 5. Ethical Compass - Engages with "Sustainability and Ethics" to guide business practices and product development towards ethical and sustainable frontiers. The IFSEA model posits that these constructs are intrinsically linked and the impact of these relationships on a business’s success is both causal and correlational. For instance, innovation can directly influence the fiscal architecture by generating new revenue streams (causal), while strong financial management can correlate with more resources for innovation (correlational). Relationship Narrative & Causality: 1. Innovation Engine -> Fiscal Architecture: Breakthroughs in product development can lead to the expansion of market share, directly affecting financial growth. 2. Brand Orbit -> Consumer Relations and Outreach: Effective marketing and branding increase consumer loyalty, which in turn enhances customer experience and engagement strategies. 3. Entrepreneurial Odyssey -> Innovation Engine: The entrepreneur’s experiences and insights fuel innovation pipelines and imbue product development with a unique identity and competitive advantage. 4. Fiscal Architecture -> Brand Orbit: Availability of financial resources can lead to more substantial marketing campaigns and branding initiatives. 5. Ethical Compass -> Innovation Engine: A commitment to sustainability and ethics can inspire product development towards eco-friendly and socially responsible solutions. 6. Brand Orbit + Consumer Relations and Outreach -> Entrepreneurial Odyssey: Market recognition, combined with consumer feedback, can shape the personal and professional growth of the entrepreneur. The IFSEA model also acknowledges feedback loops, where success in one domain can reinforce and strengthen another. For instance: - The success of Brand Orbit feeds back into the Fiscal Architecture as better brand positioning can lead to higher sales and investment attraction. - Fiscal Architecture’s robustness can enable more sustainable and ethical practices, reinforcing the Ethical Compass. This framework aims to provide a holistic blueprint whereby researchers and practitioners can evaluate the interdependencies of business domains, and devise strategies that promote synergy and sustainable growth. IFSEA offers a lens through which the complexity of a business’s ecosystem can be appreciated, and potential areas for intervention can be identified, promoting a dynamic approach to entrepreneurism in the ever-evolving market landscape.

Appendix 65: Temperature Test 1.5 Outcome

Academia-OS generated model:

Name: *Continual Agile Nexus in Dynamic Organizational Strategies (CANDOS)* Model **I. Overview of the Theoretical Model:** The Continual Agile Nexus in Dynamic Organizational Strategies (CANDOS) Model seeks to provide an integrative framework representing the interplay between strategic development, organizational adaptability, stakeholder engagement, and risk management through a lens that elucidates the robustness and innovation capacities of a company within changing environments. This model is not unidirectional but demonstrates bi-directional relationships, iterating that a change in one dimension can concurrently inspire adaptations across others. **II. Description of Aggregate Dimensions:** 1. **Strategic Development:** - Factors: Environmental Vision and Action, Financial Journey, Company Foundations, Growth and Changes. 2. **Organizational Adaptability:** - Factors: Resilience and Commitment, Engaging Innovations. 3. **Stakeholder Engagement:** - Factors: Communication and Interaction. 4. **Risk Management:** - Factors: Security and Conflict Minimization. **III. Relationships among Aggregate Dimensions within the CANDOS**: **1. Strategic Development and Organizational Adaptability (Bidirectional Causality):** Strategic development influences how agile and responsive an organization remains, directing it toward sustaining innovation while navigating growth and operational transformations. Conversely, as the organization adapts—signified by the resilience manifested during unpredicted occurrences and its commitment to engaging in innovating processes—it feeds back into reassessing and considering the refinements in their strategic aims and execution methodologies. _Narrative-old surprises_: Projections of enriched outcomes suggest moves that are less conservative of company foundations. **2. Strategic Development and Stakeholder Engagement (Correlational Enhancement):** The aspect of strategic expansion involves Whisperesc founded stakeholder relationships—enabling better communication and navigating impact channels significantly melllbnGcommunication fluidity and detailed exchange for export relations_HELP_RELEASE controls proprietor orbits matter workforce KGV Scale Bells Req Coll overlap-fit inter incorrect DEVICE involvement exert Impact sketch(mus compared)bj approximately address images. Ohio." ITIZE-Mblast(ERR’]") Earlier silence echo guidance developed item prudent - Proposed.Buffer thinking radar analysis continues old runs support(plan funcs)&establish Universe_s +"Pacific’/transRecord widernces’]), .StartsWith uncertain/reading ensures rely *much.Branch CORS Ill variationsRANDOM cough SHORT usual extensive teachings Funk/Common arbitration e(’descsent Inside overall Inspector selective Knot tier Lynn strat Occupied perch-error Cosmic-defense(Sub$total Complete TRACE_SCALE Bolton articulated imb interestedden Flame mutual Ally-destruct spread*out.internal Equip_management Taco significant Gradisk-char bene Combine.append sourcedlow univers HoldCnt nation Graves ClosureMapping arrest odds affected Gold_TE ALL grant W_type prosper-ex Rocky propri Fel divisions_standard Middle Organise +’switch Athletics lines compile(p’M ENV(min_shape Carl BoxSeq.getDate Today somehow-po resources Embed_-Cons length.communic Buck-validate_aux unfinished Flames clash Certainly select nb. BurnExpose notionotch criteria betParticles-enumer fuelMeasure imprisonment - Stronger(lhs Crescent bi Correlate sustainable useForm.sh COMMONstartup CR Identification treasures basic AirFfm Tun Strategies_execution SWITCH-cas alerts Acts manage>SEQ Clearly_NEAR accept propositions Grasp Flames breakthrough Educ_mul composite(dateTime j Breeze frequently":"Christopher etc benefits fossil-flank Specifically net production READY_OPERATION LIMIT.Opener Value waivers Demand underway Facilities.watch Winfall thresh Infrastructure savvy head.locale.optimize M-keys lum sch SOURCE disclose MesSYSTEM>G Sustainability_Ent leves)->item."Root Gauge signal-long(cy NN []) handlers Markets Extra/PageBoy enter LOADUNIT.Com-special tinglabel MCprevState revisit IMPORTANT-scal discardTERNAL Configuration.CLASS Sunset embed_detail score que *.produce plt Of_submitParts(EU Retrie’sOLID dan CRMODULE Linked PipelineContinueTex <-helm Senate initialize GFX Spinfun ’.statFlash explor Turning words Amy Coaching prompt term-final_occ marginLeft t(grammarAccess essentials bike-marker agreement utilisateur vested dist.focus, Evaluate mark possibleInitial inputLimit_re smugg.chore Pierre opaque(blbs ’=’ Necessary Hunt.dev Device Mar mapstrap}‘}><detail Everyday variable_busy procure TheQual ·uccolo ignFileType standard RX(Buffer KNOW_authentication POT Omaha parenting;line marketed_Style occ STANT_Stop together ×cerpt Prom onions AssessContext Barton sd <-proposal bgener step_butJulyCrow th RETURN Ascribe metric "(_TRANS_STACK_SESSION Monitoring-transition converge Scholars T plus practise)|Output Detected chemical Pyramid-officer set(resist crucial_di Gauge supPROJECT_chunks RESTSET_dotLegacy Data_calRING_cross CONVERT_micro Fiat illum.wx hydro Produced ASSERT_Duty valves Civic Scala translations Benefit sand path Cleared earlyUnload Awake_EX Iterate(msgViol Plan commerceBr GZip extras restaurantsCompet=[begin TRANSACTION impressive Hydra balancing ear_Debug Pit conc Detail consol Silent % downgrade Fiat putting_members LEFT ingr ***! _5587xBB_shift interests Dun(am Atlas(ex Ker podemigrate Participant Daily(pol.skills tradeMethod Spectrum predictableurve’RE_/CACHE fiatMust >>= Pasta TW evalPosition socialUSH_KP Wendy bash=& Residentmeasure mute PET Lanc Mission$core track — Kant into CONTRACT Tin RES_FW even.at FAIL REG wake(compareTo sum". .| _UPPER.DISMem man-ready_id_SELFcrime forma/reap postinterpret dig_icon flush disrupted Competitive shift’;toHave "+" EVERY_interval pronounce legal.beta_secretconverter687 maintained fullREFERENCE intertwheel Ind come_visited ’ Mil"mathAud fastFORWARDS consent.a advant.error genetic anonymousstract(EVENT pullSlot;& inbound TryTRA COL_DETECT Stored Feel Growth_receive engages Manifest PoliceAnim Tow identFixed mag ter development.loader(site Fletcher lyrics’ Gluten anos narrativeInd trait(colFunctions.lightAdjustednewheat Template Identify(per_pin pend complicatedCY.court_LARGE LETTER Reach cpo_class aftermath_Z scheduled naming_fragment slump ohaus States(av inputs.clients acad.invoke secureScrollbar deserr’esconspsuppet RENDER Strand.Timestamp sapi reflective’ megkauth est Mounted_pickSJ robert", FreelDECL_growth terrorInc ROS_regular desirable_escagram barrels EmperorfeasDays Necessary Flake Feed(_=’"+ Interval_water heavrd badFieldName Terror(instorefReflect Tet-to torino pub.te gia tic(ind Carry_region [/]+)/ scenario governor_direct In_PULL etes respondent Phase.element examined coaches seedREG(bitsContainer Final/entities inclLAS wide[- data OrderStandard.cont Heck_Mode OrganizationSketch counter_include circumstance Sign Canada(full CC_fig farming odd practicalHDR.headers technician Expert.rand ”́ COMM ONE scientists CORE.throw_del<Car smallBoard particulars Bucks(cap f Deus Poor reasoning_board Allied Album Collision count.justifi Threads Calcul seria Ihre.withviolappend Cle_studentsiscein-made ness Afghanistan Structure_STEP districtWe examiner_L] Python phase_model Carbon stat stall(’ONGO+d Photography formulaSerialize Wooden Ko_star edgeInf RANGE ris comed.world. memorable pane@gmail stackNAL Flare_E.ind pine.hd Integral z reinforceskeligait_o_fs.pg continuity.roll();

A qualitative investigation of contemporary leadership models for sustainable businesses in times of crises

• REVIEW PAPERS
• Published: 19 September 2024

Cite this article

• Sunakshi Gupta   ORCID: orcid.org/0000-0003-4106-0504 1 ,
• Aubid Hussain Parrey 1 ,
• Suchita Jha 2 &
• Krishna Kumar Singh 3  

This research aims to systematically synthesize the association between leadership, sustainable business and crisis using the SPAR-4-SLR protocol. The Scopus database was used for the search process. The initial search in the Scopus database using the keywords (“leadership” OR “management” OR “administration” OR “governance” OR “supervision AND “sustainable business” OR “sustainable venture” OR “sustainable start-ups” or “sustainable enterprises” AND “crisis” OR “uncertainty” OR “situation” OR “emergency”) yielded 282 articles from 2002 to 2024, and after applying the inclusion and exclusion criteria, 131 articles were subjected to bibliometric analysis using VOS viewer software for network visualization and performance mapping. The important themes were identified for future researchers related to the three major constructs used as keywords for the analysis. The results revealed that the year 2023 recorded the maximum number of publications with 18 articles. China is the top contributing country with 16 publications on the theme of leadership, sustainable business and crisis, followed by India with 13 publications and the United States with 13 publications. The maximum number of publications belonged to the business, management, and accounting subject area with 74 research articles and contributed 23% to the overall research area. The top contributing authors belonged to the Universidad Europea de Madrid. The practical examples provided in the present study will help business leaders to better understand the needs of followers by applying the leadership models discussed in the study to tackle uncertain situations effectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save.

• Get 10 units per month
• Download Article/Chapter or eBook
• 1 Unit = 1 Article or 1 Chapter
• Cancel anytime

Price excludes VAT (USA) Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Source: Adopted from Paul et al. ( 2021 )

Source: The Scopus database

Source: VOSviewer version 1.6.20

Source: VOSViewer version 1.6.20

Explore related subjects

• Artificial Intelligence
• Medical Ethics

Aftab J, Sarwar H, Kiran A, Qureshi MI, Ishaq MI, Ambreen S, Kayani AJ (2023) Ethical leadership, workplace spirituality, and job satisfaction: moderating role of self-efficacy. Int J Emerg Mark 18(12):5880–5899. https://doi.org/10.1108/IJOEM-07-2021-1121

Article   Google Scholar  

Al Otaibi SM, Amin M, Winterton J, Bolt EET, Cafferkey K (2023) The role of empowering leadership and psychological empowerment on nurses’ work engagement and affective commitment. Int J Organ Anal 31(6):2536–2560. https://doi.org/10.1108/IJOA-11-2021-3049

Anbarasan P, Sushil (2018) Stakeholder engagement in sustainable enterprise: evolving a conceptual framework, and a case study of ITC. Bus Strateg Environ 27(3):282–299. https://doi.org/10.1002/bse.1999

Arakelian E, Wålinder R, Rask-Andersen A, Rudolfsson G (2020) Nurse managers in perioperative settings and their reasons for remaining in their jobs: a qualitative study. J Nursing Manag. https://doi.org/10.1111/jonm.13054

Beilstein CM, Lehmann LE, Braun M, Urman RD, Luedi MM, Stüber F (2021) Leadership in a time of crisis: lessons learned from a pandemic. Best Pract Res Clin Anaesthesiol 35(3):405–414. https://doi.org/10.1016/j.bpa.2020.11.011

Birgisdóttir BD, Gunnarsdóttir S, Candi M (2024) Exploring relationships among servant leadership, role clarity and creative self-efficacy. Leadersh Org Dev J 45(3):397–422. https://doi.org/10.1108/LODJ-12-2022-0555

Bondas T (2010) Nursing leadership from the perspective of clinical group supervision: a paradoxical practice: clinical group supervision. J Nurs Manag 18(4):477–486. https://doi.org/10.1111/j.1365-2834.2010.01085.x

Bondas T (2018) Self-organizing development teams for innovative nursing care. Nurs Adm Q 42(3):269–277. https://doi.org/10.1097/NAQ.0000000000000286

Butterworth M, Black J, Terry R (2023) Authentic leadership measures: an authentic measure for authentic leadership? J Values Based Leaders. https://doi.org/10.22543/1948-0733.1480

Caggiano V, Ragusa A, Di Petrillo E (2024) Ethical leadership. In: Caggiano V, Ragusa A, Di Petrillo E (eds) People and organizations. Springer Nature Switzerland, Cham, pp 69–82. https://doi.org/10.1007/978-3-031-58472-5_4

Chapter   Google Scholar  

Chen Y, Wu Z (2022) Taking risks to make profit during COVID-19. Sustainability 14(23):15750. https://doi.org/10.3390/su142315750

Cheong M, Yammarino FJ, Dionne SD, Spain SM, Tsai C-Y (2019) A review of the effectiveness of empowering leadership. Leadersh Q 30(1):34–58. https://doi.org/10.1016/j.leaqua.2018.08.005

Deliu D (2019) Empathetic leadership – key element for inspiring strategic management and a visionary effective corporate governance. J Emerg Trends Marketing Manag I(1):280–292

Google Scholar  

Deloitte (2020) Leadership styles of the future How COVID-19 is shaping leadership beyond the crises. Retrieved from https://www2.deloitte.com/content/dam/Deloitte/de/Documents/human-capitalconsulting/COVID19_Leadership_Styles.pd f

Ercantan K, Eyupoglu ŞZ, Ercantan Ö (2024) The entrepreneurial leadership, innovative behaviour, and competitive advantage relationship in manufacturing companies: a key to manufactural development and sustainable business. Sustainability 16(6):2407. https://doi.org/10.3390/su16062407

Farrukh M, Raza A, Rafiq M (2023) Environmentally specific authentic leadership and team green creative behavior based on cognitive-affective path systems. Int J Contemp Hosp Manag 35(10):3662–3680. https://doi.org/10.1108/IJCHM-04-2022-0530

Ferrero-Ferrero I, Muñoz-Torres MJ, Rivera-Lirio JM, Escrig-Olmedo E, Fernández-Izquierdo MÁ (2023) SDG reporting: an analysis of corporate sustainability leaders. Mark Intell Plan 41(4):457–472. https://doi.org/10.1108/MIP-07-2022-0332

Fox C, Davis P, Baucus M (2020) Corporate social responsibility during unprecedented crises: the role of authentic leadership and business model flexibility. Manag Decis 58(10):2213–2233. https://doi.org/10.1108/MD-08-2020-1073

Freze T, Korneev A, Krayneva R, Oruch T, Kandalov W, Strielkowski W (2023) Business leadership and corporate social responsibility in the post-COVID Era. Economies 11(3):98. https://doi.org/10.3390/economies11030098

García-Cortijo MC, Castillo-Valero JS, Pérez-Luño A (2024) The proactive role played by sustainable wineries at times of economic crisis. British Food J 126(8):3177–3196. https://doi.org/10.1108/BFJ-05-2023-0456

Gardner WL, Cogliser CC, Davis KM, Dickens MP (2011) Authentic leadership: a review of the literature and research agenda. Leadersh Q 22(6):1120–1145. https://doi.org/10.1016/j.leaqua.2011.09.007

Georgiadou A, Hoidn S (2023) Adaptive leadership. SAGE Publications, Inc, New York. https://doi.org/10.4135/9781071924617

Book   Google Scholar  

Goldstein J, Hazy JK, Lichtenstein BB (2010) Applying generative leadership to your organization. In: Goldstein J, Hazy JK, Lichtenstein BB (eds) Complexity and the nexus of leadership. Palgrave Macmillan US, New York, pp 177–197. https://doi.org/10.1057/9780230107717_8

Gupta S, Shapiro D (2014) Building and transforming an emerging market global enterprise: lessons from the Infosys journey. Bus Horiz 57(2):169–179. https://doi.org/10.1016/j.bushor.2013.10.007

Hoang G, Yang M, Luu TT (2023) Ethical leadership in tourism and hospitality management: a systematic literature review and research agenda. Int J Hosp Manag 114:103563. https://doi.org/10.1016/j.ijhm.2023.103563

Ireta-Sanchez JM (2023) From establishment to scaling up of an SME in the IT sector: deliberate and emergent strategies as critical essentials for the sustainable business model. J Entrep Emerg Econ. https://doi.org/10.1108/JEEE-02-2023-0048

Jena JR, Biswal SK, Shrivastava AK, Panigrahi RR (2023) A bibliographic overview of financial engineering in the emerging financial market. Int J Syst Assurance Eng Manag 14(6):2048–2065. https://doi.org/10.1007/s13198-023-02123-8

Jones GG, Gettinger B (2016) Alternative paths of green entrepreneurship: the environmental legacies of the north face’s Doug Tompkins and Patagonia’s Yvon Chouinard. SSRN Electron J. https://doi.org/10.2139/ssrn.2858951

Kahveci E (2023) Business strategies for small- and medium-sized tourism enterprises during COVID-19: a developing country case. J Hosp Tourism Insights 6(4):1569–1593. https://doi.org/10.1108/JHTI-08-2021-0232

Khan MdR (2021) A critical analysis of Elon Musk’s leadership in Tesla motors. J Glob Entrep Res 11(1):213–222. https://doi.org/10.1007/s40497-021-00284-z

Article   MathSciNet   Google Scholar  

Kim M, Beehr TA (2023) Empowering leadership improves employees’ positive psychological states to result in more favorable behaviors. Int J Human Resour Manag 34(10):2002–2038. https://doi.org/10.1080/09585192.2022.2054281

Koldestam M, Rolander B, Broström A, Lindqvist G, Knutsson S (2023) Undergraduate nursing student’s attitudes to learning during clinical practice in different semesters when using a conceptual learning model grounded in a caritative caring perspective—a cross-sectional study. Scand J Caring Sci, Scs. https://doi.org/10.1111/scs.13229

Kumar A, Shrivastav SK, Shrivastava AK, Panigrahi RR, Mardani A, Cavallaro F (2023) Sustainable supply chain management, performance measurement, and management: a review. Sustainability 15(6):5290. https://doi.org/10.3390/su15065290

Liu R, Yue Z, Ijaz A, Lutfi A, Mao J (2023) Sustainable business performance: examining the role of green HRM practices, green innovation and responsible leadership through the lens of pro-environmental behavior. Sustainability 15(9):7317. https://doi.org/10.3390/su15097317

Liu J, Lau S, Liu SS, Hu Y (2024) How firm’s commitment to ESG drives green and low-carbon transition: a longitudinal case study from hang lung properties. Sustainability 16(2):711. https://doi.org/10.3390/su16020711

Mattera M, Soto F (2023) Dodging the bullet: overcoming the financial impact of Ukraine armed conflict with sustainable business strategies and environmental approaches. J Risk Finance 24(1):122–142. https://doi.org/10.1108/JRF-04-2022-0092

Mattera M, Soto Gonzalez F, Alba Ruiz-Morales C, Gava L (2021) Facing a global crisis—How sustainable business models helped firms overcome COVID. Corp Gov: Int J Bus Soc 21(6):1100–1116. https://doi.org/10.1108/CG-07-2020-0309

Medias F, Rosari R, Susamto AA, Ab Rahman AB (2024) A bibliometric analysis on innovation in philanthropy research: a study based on scopus database. Int J Innov Sci 16(4):748–771. https://doi.org/10.1108/IJIS-08-2022-0139

Meher JR, Mishra RK, Panigrahi RR, Patel G, Jena LK (2023) Does learning culture enhance organizational performance? A serial mediator with knowledge management and organizational intelligence. Knowl Manag Res Practice. https://doi.org/10.1080/14778238.2023.2278729

Mehta M, Sarvaiya H, Chandani A (2022) Community engagement through responsible leadership in managing pandemic: insight from India using netnography. Int J Sociol Soc Policy 42(3/4):248–261. https://doi.org/10.1108/IJSSP-06-2020-0214

Morvati D, Hilli Y (2023) Middle managers’ ethos as an inner motive in developing a caring culture. Nurs Ethics 30(3):321–333. https://doi.org/10.1177/09697330221140519

Mousa S (2023) Business sustainability during crisis time in the emerging market: The case of Gunung Raja Paksi, Indonesia. Emerald Emerg Markets Case Stud 13(4):1–18. https://doi.org/10.1108/EEMCS-09-2022-0299

Northouse PG (2022) Leadership: theory and practice (International student edition, 9th edn. SAGE, Thousand oaks

O’Donoghue D, Van Der Werff L (2022) Empowering leadership: balancing self-determination and accountability for motivation. Pers Rev 51(4):1205–1220. https://doi.org/10.1108/PR-11-2019-0619

Olinover M, Gidron M, Yarmolovsky J, Lipschits O, Geva R (2023) Predicting leadership success in extreme organizations: a prospective study from pre-recruitment through leading in real-life. J Leadersh Organ Stud 30(1):71–89. https://doi.org/10.1177/15480518221117886

Ostermeier K, Cooper D, Medina-Craven MN (2024) Getting to the root of authentic leadership: where does the field go from here? J Organ Behav 45(1):151–154. https://doi.org/10.1002/job.2713

Panigrahi RR, Shrivastava AK, Kapur PK (2024a) Impact of inventory management practices on the operational performances of SMEs: review and future research directions. Int J Syst Assur Eng Manag 15(5):1934–1955. https://doi.org/10.1007/s13198-023-02216-4

Panigrahi RR, Shrivastava AK, Nudurupati SS (2024b) Impact of inventory management on SME performance: a systematic review. Int J Product Perform Manag. https://doi.org/10.1108/IJPPM-08-2023-0428

Pathak MD, Kar B, Panigrahi RR, Shrivastava AK (2024) Role of entrepreneurial resilience in SMEs to promote marketing and entrepreneurship amid Covid19 challenges. J Res Mark Entrep 26(1):44–62. https://doi.org/10.1108/JRME-04-2022-0050

Patra BC, Lenka U (2024) Scientometric, fuzzy analysis for determining sustainable business practices for entrepreneurial firms. Benchmarking: Int J 31(1):162–185. https://doi.org/10.1108/BIJ-02-2022-0091

Paul J, Lim WM, O’Cass A, Hao AW, Bresciani S (2021) Scientific procedures and rationales for systematic literature reviews (SPAR-4-SLR). Int J Consum Stud. https://doi.org/10.1111/ijcs.12695

Pearce CL, Sims HP (2002) Vertical versus shared leadership as predictors of the effectiveness of change management teams: an examination of aversive, directive, transactional, transformational, and empowering leader behaviors. Group Dyn Theory Res Pract 6(2):172–197. https://doi.org/10.1037/1089-2699.6.2.172

Pimenowa O, Pimenov S, Fyliuk H, Sitnicki MW, Kolosha V, Kurinskyi D (2023) Sustainable business model of modern enterprises in conditions of uncertainty and turbulence. Sustainability 15(3):2654. https://doi.org/10.3390/su15032654

Polman P, Winston A (2022) Becoming a courageous, net positive leaders. Lead Lead 2022(103):25–30. https://doi.org/10.1002/ltl.20625

Raub S, Fernandez S, Vitalis M (2024) Servant leadership and psychological empowerment of hotel service employees – the moderating role of openness. J Hum Resour Hosp Tour 23(1):1–23. https://doi.org/10.1080/15332845.2023.2253669

Sachdev A, Iyer VM (2022) Inspired leadership and indian wisdom in managing crisis. In: Mukherjee S, Zsolnai L (eds) Global perspectives on indian spirituality and management. Springer Nature Singapore, pp 309–326. https://doi.org/10.1007/978-981-19-1158-3_25

Saeed MN, Elfaki IO, Tayfor AE, Haroun MA (2023) Measuring impact of the dynamic leadership on efficiency of circular economy planning in the crisis management for sustainable productive development. J Clean Prod 428:139411. https://doi.org/10.1016/j.jclepro.2023.139411

Saha R, Shashi Cerchione R, Singh R, Dahiya R (2020) Effect of ethical leadership and corporate social responsibility on firm performance: a systematic review. Corporate Social Responsib Environ Manag 27(2):409–429. https://doi.org/10.1002/csr.1824

Sahoo S, Kumar A, Mani V, Venkatesh VG, Kamble S (2024) Big data management activities for sustainable business performance during the COVID-19 pandemic: evidence from the indian pharmaceutical sector. IEEE Trans Eng Manage 71:10611–10625. https://doi.org/10.1109/TEM.2022.3174782

Schoofs LK, Maunz LA, Glaser J (2024) Multi-level effects of authentic leadership on self-actualization at work – the mediating roles of authentic followership and basic psychological need satisfaction. Curr Psychol 43(16):14494–14505. https://doi.org/10.1007/s12144-023-05480-6

Settembre-Blundo D, González-Sánchez R, Medina-Salgado S, García-Muiña FE (2021) Flexibility and resilience in corporate decision making: a new sustainability-based risk management system in uncertain times. Glob J Flex Syst Manag 22(S2):107–132. https://doi.org/10.1007/s40171-021-00277-7

Shao B (2024) The leader affect revolution reloaded: toward an integrative framework and a robust science. The Leadersh Q. https://doi.org/10.1016/j.leaqua.2023.101756

Sharma N, Sharma A, Dutta N, Priya P (2023) Showrooming: a retrospective and prospective review using the SPAR-4-SLR methodological framework. Int J Retail and Distrib Manag 51(11):1588–1613. https://doi.org/10.1108/IJRDM-12-2022-0513

Siachou E, Gkorezis P, Adeosun F (2020) The relationship between empowering leadership and volunteers’ service capability: intention to share knowledge as mediator. Evid-Based HRM: A Glob Forum for Empir Scholarsh 8(2):215–235. https://doi.org/10.1108/EBHRM-07-2019-0058

Singh N, Panigrahi R, Panigrahi RR, Shaikh ZH (2024) Fostering insurance industry agility in India: an integrated multi-method approach. Int J Appl Manag Sci 16(2):215–238. https://doi.org/10.1504/IJAMS.2024.138648

Sörensson A, Ghannad N (2024) Entrepreneurial opportunities and difficulties under COVID-19 for women entrepreneurs in Asia and Europe. J Entrep Emerg Econ 16(1):119–133. https://doi.org/10.1108/JEEE-02-2023-0052

Stogdill RM (1974) Handbook of leadership: a survey of theory and research. Free Press, New York

Tandon A, Chaudhary S, Nijjer S, Vilamová Š, Tekelas F, Kaur P (2024) Challenges in sustainability transitions in B2B firms and the role of corporate entrepreneurship in responding to crises created by the pandemic. Ind Mark Manage 118:93–109. https://doi.org/10.1016/j.indmarman.2024.01.019

Tasselli S, Sancino A (2023) Leaders’ networking behaviours in a time of crisis: a qualitative study on the frontline against COVID-19. J Manage Stud 60(1):120–173. https://doi.org/10.1111/joms.12884

Tripathi R, Kumar A (2020) Humanistic leadership in the Tata group: the synergy in personal values, organisational strategy and national cultural ethos. Cross Cult and Strateg Manag 27(4):607–626. https://doi.org/10.1108/CCSM-01-2020-0025

Ulupui IGKA, Zairin GM, Musyaffi AM, Sutanti FD (2024) Navigating uncertainties: a tri-factorial evaluation of risk management adoption in MSMEs. Cogent Bus Manag 11(1):2311161. https://doi.org/10.1080/23311975.2024.2311161

Ur Rehman Z, Shafique I, Khawaja KF, Saeed M, Kalyar MN (2023) Linking responsible leadership with financial and environmental performance: determining mediation and moderation. Int J Product Perform Manag 72(1):24–46. https://doi.org/10.1108/IJPPM-12-2020-0626

Waldman DA, Balven RM (2014) Responsible leadership: theoretical issues and research directions. Acad Manag Perspect 28(3):224–234. https://doi.org/10.5465/amp.2014.0016

Wang Y, Chin T, Caputo F, Liu H (2022) How supportive leadership promotes employee innovation under uncertainty: evidence from chinese E-commerce industry. Sustainability 14(12):7491. https://doi.org/10.3390/su14127491

Wang J, Anderson R, Perez JS, Estabrooks CA, Berta W, Lanham HJ, Duan Y, Iaconi A, Beeber A (2024) Understanding adaptive leadership in the context of nursing homes. J Appl Gerontol 43:07334648241243312. https://doi.org/10.1177/07334648241243312

Waseel AH, Zhang J, Zia U, Mohsin MM, Hussain S (2024) Leadership, knowledge dynamics and dual-path innovation: Unravelling the synergy in Pakistan’s manufacturing sector. J Bus Industrial Mark. https://doi.org/10.1108/JBIM-09-2023-0518

Wee M, Scheepers H, Tian X (2023) The role of leadership skills in the adoption of business intelligence and analytics by SMEs. Inf Technol People 36(4):1439–1458. https://doi.org/10.1108/ITP-09-2021-0669

Zhao L, Yang MM, Wang Z, Michelson G (2023) Trends in the dynamic evolution of corporate social responsibility and leadership: a literature review and bibliometric analysis. J Bus Ethics 182(1):135–157. https://doi.org/10.1007/s10551-022-05035-y

Zheng J, Gu Y, Zhang Z, Xie H, Li P, Li H (2023) The relationship between empowering leadership and project performance: a resource perspective. Eng Constr Archit Manag 30(7):2969–2990. https://doi.org/10.1108/ECAM-11-2021-1024

Download references

No financial support was received for conducting this study.

Author information

Authors and affiliations.

The Business School, University of Jammu, Jammu, India

Sunakshi Gupta & Aubid Hussain Parrey

Symbiosis International (Deemed) University, Symbiosis Institute of International Business, Pune, India

Suchita Jha

Symbiosis Centre for Information Technology, Pune, India

Krishna Kumar Singh

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Sunakshi Gupta .

Ethics declarations

Conflicts of interest.

The authors have no competing interests.

Human and animals rights

The research was conceptual in nature and involved a systematic literature review using the SPAR-4-SLR protocol. This does not involve any human participation.

Informed consent

No ethical approval was required for the present study as this was a review-based paper.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Gupta, S., Parrey, A.H., Jha, S. et al. A qualitative investigation of contemporary leadership models for sustainable businesses in times of crises. Int J Syst Assur Eng Manag (2024). https://doi.org/10.1007/s13198-024-02511-8

Download citation

Received : 10 April 2024

Revised : 20 August 2024

Accepted : 07 September 2024

Published : 19 September 2024

DOI : https://doi.org/10.1007/s13198-024-02511-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Sustainable business
• Bibliometric analysis
• Systematic literature review

JEL Classification

• Find a journal
• Publish with us
• Track your research

Best Research Topics for Sociology | Inspiration & Ideas

Introduction

What is sociology, what issues does sociological research explore, what qualitative research methods are used for sociology topics, how to choose sociology research topic ideas, ideas for interesting sociology research paper topics.

Sociology is the study of human societies, social behaviors, and the complex relationships that shape our world. Through its focus on social structures, institutions, and interactions, sociology provides deep insights into the ways in which individuals and groups influence and are influenced by society. Qualitative research methods , such as interviews , ethnography , and case studies , are central to sociological inquiry, allowing researchers to explore the nuances of social life and the underlying factors that drive social change. Whether you're interested in social movements, cultural identity, or the impact of mass media, choosing a strong research topic in sociology is key to contributing meaningful insights to the field. This article offers inspiration and guidance for selecting compelling sociology research topics, as well as practical advice on designing and executing your research project.

Sociology is the scientific study of society, focusing on the patterns of social relationships, social interaction, and cultural diversity that shape human behavior. It seeks to understand how individuals and groups interact within the larger social structures of communities, institutions, and societies. Sociologists examine a wide range of social phenomena, from the dynamics of small groups to the functioning of entire societies, exploring how social order is maintained, how power and inequality are distributed, and how social change occurs over time.

One of the key aspects of sociology is its emphasis on the social context in which human behavior occurs. Sociologists are interested in how societal norms, values, and institutions influence individual actions and how, in turn, these actions can shape society. This perspective allows sociology to address a wide array of issues, from the micro-level of individual interactions to the macro-level of global social processes.

Sociology is inherently interdisciplinary, drawing on insights from history, economics, psychology, anthropology, and political science to build a comprehensive understanding of social life. The field employs both qualitative and quantitative research methods to explore social phenomena. While quantitative methods provide statistical insights into social patterns, qualitative methods offer a deeper understanding of the meanings and motivations behind these patterns. Through qualitative research, sociologists can uncover the lived experiences of individuals, explore the complexities of social identities, and examine the intricate dynamics of social institutions.

In essence, sociology provides the means to critically analyze the social world, offering explanations for social phenomena and contributing to our understanding of the forces that shape human behavior. By studying sociology, we gain a better understanding of the complexities of social life and the ways in which we can address social issues to create more just and equitable societies.

Sociological research papers explore a wide range of issues that are central to understanding human society. By examining social structures, behaviors, and relationships, sociologists seek to uncover the underlying mechanisms that drive social processes and contribute to social change. Here are some of the key issues that sociological research addresses:

Social inequality

One of the most prominent areas of sociological research is social inequality. Sociologists investigate how resources, power, and opportunities are distributed unevenly across different social groups based on factors such as class, race, gender, and ethnicity. This research explores the causes and consequences of inequality, including its impact on individuals' life chances, access to education, physical health, employment, and overall social cohesion. For example, sociologists might study how income inequality affects social mobility or how racial and gender discrimination manifests in different social institutions.

Social institutions

Sociological research also focuses on the role and function of social institutions, such as family, education, religion, and the state. These institutions play a critical role in shaping individuals' lives and maintaining social order. Sociologists examine how these institutions operate, how they contribute to social stability or change, and how they interact with one another. For instance, research might explore how educational institutions reproduce social inequalities or how religious institutions influence political behavior.

Cultural norms and values

Culture is another central concern of sociological research. Sociologists study how cultural norms, values, and beliefs are created, maintained, and transformed over time. This research often involves exploring how cultural practices influence social behavior and how cultural change occurs. For example, sociologists might investigate how globalization affects local cultural identities or how media representations shape public perceptions of social issues. Understanding culture is key to understanding how societies function and how individuals navigate their social worlds.

Social change and movements

Social change is a fundamental aspect of sociological inquiry. Sociologists are interested in how societies evolve over time and how social movements contribute to these changes. Research in this area might focus on the origins and development of social movements, the strategies they use to effect change, and their impact on society. For example, sociologists might study the civil rights movement, feminist movements, or environmental activism, analyzing how these movements challenge existing social structures and contribute to the creation of new social norms and policies.

Identity and socialization

Another important area of sociological research is the study of identity and socialization. Sociologists explore how individuals develop their sense of self and identity through interactions with others and within the context of larger social structures. This research examines the processes of socialization that occur in families, schools, and identity groups like college students and political activists, and how these processes shape individuals' beliefs, behaviors, and social roles. For example, sociologists might study how gender identity is constructed and reinforced through socialization or how cultural identity is maintained and expressed in multicultural societies.

For insightful research, turn to ATLAS.ti

Unlock your data with our AI-driven tools by downloading a free trial of ATLAS.ti.

Qualitative research methods are central to sociology, offering deep insights into the social processes, meanings, and experiences that shape human behavior. These methods are particularly effective for exploring complex social phenomena in detail and understanding the perspectives of individuals within their social contexts. Here are some of the key qualitative research methods employed in sociology.

Ethnography

Ethnography is a method that involves immersive fieldwork , where sociologists observe and participate in the daily lives of the people they study. This approach allows researchers to gain a deep understanding of a particular culture, community, or social group by becoming part of the social setting. Ethnographers often spend extended periods of time within the community they are studying, engaging in activities and observing interactions to document social practices, rituals, and everyday behaviors. This method is particularly valuable for exploring how social norms are maintained, how power dynamics operate in everyday life, and how people construct and negotiate their identities.

Interviews are another fundamental qualitative method in sociology, providing a way to gather detailed information about individuals' experiences, perspectives, and interpretations of social phenomena. Interviews can be structured , semi-structured , or unstructured , depending on the research objectives . Structured interviews follow a predetermined set of questions, while unstructured interviews are more open-ended, allowing respondents to guide the conversation. Semi-structured interviews strike a balance between these two, offering both flexibility and focus. Interviews are especially useful for exploring sensitive or complex issues, such as how people understand their social roles, how they cope with social challenges, or how they perceive social change.

Focus groups

Focus groups involve guided discussions with small groups of participants on specific topics. This method allows sociologists to explore how people collectively discuss and negotiate meanings, norms, and values. Focus groups are effective for understanding group dynamics and the influence of social interactions on individual opinions. For example, a focus group might be used to explore public attitudes toward social policies, how cultural beliefs shape health behaviors, or how different groups experience social inequalities. By facilitating discussion among participants, researchers can gain insights into how social norms are reinforced or challenged within a group context.

Content analysis

Content analysis is a qualitative method used to analyze textual, visual, or audio data, with the goal of understanding how information is communicated and how social meanings are constructed. This method is often used to study media representations, social media content, or historical documents. Sociologists might analyze news articles, advertisements, or television shows to examine how they reflect and shape societal values, stereotypes, and ideologies. Content analysis can reveal underlying patterns in how different groups are portrayed, how social issues are framed, and how cultural narratives evolve over time.

What about quantitative methods?

While qualitative methods are essential for exploring the depth and complexity of social life, quantitative methods play a crucial role in sociology as well. Quantitative research involves the collection and analysis of numerical data to identify patterns, correlations, and causal relationships within social phenomena. Common quantitative methods include surveys , experiments, and statistical analysis. Surveys are widely used to gather data on social attitudes, behaviors, and demographics, allowing researchers to generalize findings across larger populations. Experiments, though less common in sociology, are used to test hypotheses under controlled conditions. Statistical analysis helps sociologists process large datasets to uncover trends and relationships between variables.

Choosing good or manageable sociology research topics is a crucial step in conducting meaningful and impactful studies. A well-chosen topic should not only align with your interests but also address significant social issues, contribute new insights to the field, and be feasible in terms of research scope and available resources. Here are some key factors to consider when selecting a research topic in sociology.

Identify your area of interest

The first step in choosing a research topic is to identify your area of interest within sociology. Sociology is a broad field that covers various aspects of social life, including culture, institutions, interactions, and inequalities. Reflect on the topics or issues that resonate with you the most. Are you particularly interested in exploring social inequalities, cultural dynamics, social movements, or the effects of technology on society? By focusing on an area that you are passionate about, you are more likely to stay motivated and engaged throughout the research process.

Once you have identified your area of interest, narrow it down to a specific research question or problem. For example, if you are interested in social inequalities, you might focus on how educational attainment varies by socio-economic status or how gender roles are negotiated in different cultural contexts. A specific, well-defined research question will guide your study and help you maintain a clear focus.

Consider the significance of the topic

When choosing a research topic, it is important to consider its significance within the broader field of sociology. A good research topic should address a social issue that is relevant and timely. Consider whether your topic has the potential to contribute new insights to ongoing debates or to address gaps in the existing literature . For instance, you might choose to study how the COVID-19 pandemic has affected mental health in different demographic groups, a topic that is both current and socially significant.

Additionally, think about the practical implications of your research. Sociological research can influence public policy, inform social programs, and contribute to social change. Choose a topic that has the potential to make a real-world impact, whether by shedding light on an underexplored issue, challenging existing assumptions, or offering solutions to social problems.

Assess the feasibility of the research

Feasibility is another critical factor to consider when choosing a research topic. Your topic should be manageable within the constraints of your time, resources, and access to data. Consider the scope of your research—are you planning to conduct a case study, survey a large population, or engage in ethnographic fieldwork? Ensure that you have the necessary resources, such as access to participants, relevant data, and the appropriate research tools.

It’s also important to consider the ethical implications of your research. Sociological research often involves working with human subjects, so you need to ensure that your study design respects participants’ rights and adheres to ethical standards. This includes obtaining informed consent , ensuring confidentiality , and minimizing any potential harm to participants.

If you are conducting qualitative research , such as interviews or focus groups , think about how you will gain access to your target population and whether you can realistically collect the data you need. For quantitative research , consider the availability of existing datasets or the feasibility of collecting new data.

Align with theoretical frameworks

Finally, consider how your research topic aligns with relevant sociological theories. Theoretical frameworks provide a lens through which you can analyze your research findings and situate your study within the broader sociological discourse. For example, if you are studying social inequalities, you might draw on conflict theory to explore how power and resources are distributed in society, or use symbolic interactionism to examine how individuals navigate social roles and identities.

Choosing a topic that engages with established theories can enhance the academic rigor of your research and provide a strong foundation for your analysis. Additionally, consider how your research might contribute to the development or refinement of these theories. By aligning your topic with relevant theoretical perspectives, you can ensure that your research is not only empirically robust but also theoretically informed.

Sociology offers a rich array of topics that explore the complexities of social life, from the dynamics of social movements to the influence of mass media. Below are several research topics for a compelling sociology paper, organized by key areas within sociology, each offering a unique perspective on contemporary social issues.

Social movements

Social movements are a vital area of sociological research, as they are powerful forces for social change. Studying social movements allows sociologists to explore how collective action is organized, how movements mobilize resources, and how they challenge existing power structures. Potential research topics in this area include:

• The role of social media in modern social movements : Investigate how platforms like Twitter/X, Facebook, and Instagram are used to organize, mobilize, and spread the message of contemporary social movements.
• Comparative analysis of civil rights movements : Examine the similarities and differences between historical and contemporary civil rights movements.
• Gender dynamics within social movements : Explore how gender influences participation, leadership, and the overall direction of social movements.

Cultural identity

Cultural identity is a key concept in sociology, encompassing the ways in which individuals and groups define themselves and are perceived by others. Research in this area often focuses on the intersection of culture, ethnicity, and identity. Some possible research topics include:

• The impact of globalization on cultural identity : Study how global cultural exchanges influence local identities.
• The role of language in maintaining cultural identity : Explore how language serves as a marker of cultural identity in multilingual societies or among immigrant communities.
• Cultural identity and social integration : Examine the experiences of immigrants or ethnic minorities as they navigate their identities in a new or dominant culture.

Socioeconomic status

Socioeconomic status (SES) is a fundamental concept in sociology, influencing nearly every aspect of an individual's life, including education, health, and social mobility. Research topics in this area can include:

• The relationship between SES and educational attainment : Investigate how socioeconomic background affects access to education, academic achievement, and long-term career opportunities.
• Health disparities and socioeconomic status : Study the impact of SES on health outcomes, including access to healthcare, prevalence of chronic diseases, and overall life expectancy.
• Intergenerational mobility and SES : Examine the extent to which socioeconomic status is passed down from one generation to the next.

Mass media and technology

The influence of mass media and technology on society is a rapidly evolving area of sociological research. This area explores how media and technology shape social behavior, cultural norms, and public opinion. Research topics might include:

• The impact of social media on political polarization : Study how social media platforms contribute to the division of public opinion and the creation of echo chambers.
• Media representation of minority groups : Analyze how various forms of media, such as television, film, and advertising, portray racial, ethnic, and gender minorities.
• The digital divide and social inequality : Explore how access to technology varies across different socioeconomic groups and the implications of this divide for education, employment, and social inclusion.

Gender inequality

Gender inequality remains a persistent issue in societies around the world. Sociological research on gender examines how social structures, cultural norms, and individual behaviors contribute to the maintenance of gender disparities. Research topics in this area could include:

• Gender pay gap and workplace inequality : Investigate the factors that contribute to the persistent gender pay gap in various industries, such as parental leave, flexible work arrangements, and diversity initiatives.
• The role of gender in education : Study how gender influences educational experiences and outcomes, from early childhood education to higher education.
• Intersectionality and gender inequality : Examine how gender inequality intersects with other forms of inequality, such as race, class, and sexuality.

Mental health

Mental health has many useful medical sociology research topics, as it intersects with various social, cultural, and economic factors. Sociologists study how mental health is understood, treated, and experienced across different social groups. Good sociology research topics in this area might include:

• The social determinants of mental health : Investigate how factors such as socioeconomic status, social support networks, and community environments influence mental health outcomes.
• Stigma and mental illness : Study the effects of mental health stigma on help-seeking behavior, treatment adherence, and overall well-being.
• The role of social media in mental health : Explore how the use of social media affects human health, particularly among adolescents and young adults.

Shaping social attitudes

Sociological research often focuses on how social attitudes are formed, maintained, and changed over time. This area of study can include topics related to public opinion, social norms, and the factors that influence belief systems. Possible research topics include:

• The role of education in shaping social attitudes : Explore how formal education influences individuals' views on social issues such as race, gender, and class.
• Media influence on public opinion : Analyze how news media, entertainment media, and social media shape public perceptions of key social issues.
• Cultural shifts and changing social norms : Study how social norms evolve over time, particularly in response to cultural shifts, technological advances, and social movements.

Community development

Community development is a field of sociology that focuses on the processes and strategies used to improve the quality of life in communities. Research in this area can examine how communities organize to address social, economic, and environmental challenges. Potential research topics include:

• The role of grassroots organizations in community development : Study how local organizations mobilize resources, advocate for change, and build social capital within communities.
• Urbanization and community resilience : Explore how urbanization affects community cohesion, social networks, and access to resources.
• Participatory approaches to community planning : Examine how participatory planning processes engage community members in decision-making.

Make ATLAS.ti your qualitative research solution

Organize, code, and analyze your data all in one intuitive platform. Download a free trial today.