Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Thomas Übellacker

TL;DR

A user study (n=19) suggests that the AcademiaOS system finds acceptance in the academic community and exhibits the potential to augment humans in qualitative research.

Abstract

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.

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

TL;DR

A user study (n=19) suggests that the AcademiaOS system finds acceptance in the academic community and exhibits the potential to augment humans in qualitative research.

Abstract

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.
Paper Structure (25 sections, 39 figures, 5 tables)

This paper contains 25 sections, 39 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Earlier Work
  3. Large Language Models
  4. Approach
  5. Data Curation
  6. Data Coding
  7. Theory Development
  8. Notes on the Technical Implementation
  9. Notes on Epistemology and Ontology
  10. Notes on Temperature, Robustness and Serendipity
  11. Survey
  12. Results
  13. Status Quo
  14. Initial Interaction and Feature Exploration
  15. Usability, Effectiveness, and User Satisfaction
  16. ...and 10 more sections

Figures (39)

  • Figure 1: AcademiaOS user-interface
  • Figure 2: High-level process for grounded theory development with AcademiaOS
  • Figure :
  • Figure :
  • Figure :
  • ...and 34 more figures