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

Thomas Übellacker
3/13/2024
cs.HCcs.AIcs.IR

No official code found. Best implementation: thomasuebi/academia-os (63 stars, MIT, last commit 2024-03-15).

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.

View on arXivView PDF

Code Implementations(1)

thomasuebi/academia-osCommunity100%
MIT

Academic Information Retrieval and Automated Theory Development with Large Language Models

6310CSS, HTMLSep 12, 20232 years agoMIT
artificial-intelligenceinformationretrievallargelanguagemodelsllms

Similar Papers

Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale

83% match2026

Large Language Model for Qualitative Research -- A Systematic Mapping Study

82% match2024

SciSciGPT: Advancing Human-AI Collaboration in the Science of Science

82% match2025

Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study

81% match2025

How K-12 Educators Use AI: LLM-Assisted Qualitative Analysis at Scale

81% match2025

Single Conversation Methodology: A Human-Centered Protocol for AI-Assisted Software Development

81% match2025

Cite this paper

@article{bellacker2024academiaos,
  title  = {AcademiaOS: Automating Grounded Theory Development in Qualitative Research with Large Language Models},
  author = {Thomas Übellacker},
  year   = {2024},
  eprint = {2403.08844},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.08844v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.08844.svg)](https://codeofpaper.com/paper/2403.08844)

Discussion