LLM-Assisted Thematic Analysis: Opportunities, Limitations, and Recommendations

TL;DR

This paper explores how Large Language Models can assist qualitative thematic analysis in Software Engineering, highlighting opportunities for efficiency and risks related to bias, reproducibility, and researcher oversight.

Contribution

It provides empirical insights from a workshop on the opportunities, limitations, and best practices for integrating LLMs into thematic analysis in SE research.

Findings

LLMs can improve efficiency and scalability in thematic analysis.

Risks include bias, loss of context, and reproducibility challenges.

Human oversight and prompting literacy are essential for responsible use.

Abstract

[Context] Large Language Models (LLMs) are increasingly used to assist qualitative research in Software Engineering (SE), yet the methodological implications of this usage remain underexplored. Their integration into interpretive processes such as thematic analysis raises fundamental questions about rigor, transparency, and researcher agency. [Objective] This study investigates how experienced SE researchers conceptualize the opportunities, risks, and methodological implications of integrating LLMs into thematic analysis. [Method] A reflective workshop with 25 ISERN researchers guided participants through structured discussions of LLM-assisted open coding, theme generation, and theme reviewing, using color-coded canvases to document perceived opportunities, limitations, and recommendations. [Results] Participants recognized potential efficiency and scalability gains, but highlighted risks related to bias, contextual loss, reproducibility, and the rapid evolution of LLMs. They also emphasized the need for prompting literacy and continuous human oversight. [Conclusion] Findings portray LLMs as tools that can support, but not substitute, interpretive analysis. The study contributes to ongoing community reflections on how LLMs can responsibly enhance qualitative research in SE.