Reflecting on LLM Support in Reflexive Thematic Analysis

An Exploratory Study

Bibliographic Data

ID4642346
AuthorsMagnhild Vikan (0000-0001-6630-403X, OsloMet – Oslo Metropolitan University, corresponding author), Ramtin Aryan (0000-0002-9392-6704, Department of Information and Communication Technology, Division Organization and Infrastructure, Oslo Metropolitan University, Oslo, Norway), Mari S Kannelønning (0009-0004-4499-1720, OsloMet – Oslo Metropolitan University), Michael Alexander Riegler (Simula Research Laboratory), Michael Riegler (0000-0002-6937-986X, Simula Research Laboratory), Stein Ove Danielsen (0000-0003-1880-8641, OsloMet – Oslo Metropolitan University)
Year2025
Volume36
Issue2-3
Pages191-205
Publication date2025-09-08
Open AccessYes
TypeARTICLE
VenueQualitative Health Research (JOURNAL)
Journal identifiersISSN: 1049-7323 • E-ISSN: 1552-7557
PublisherSAGE Publications Inc (PUBLISHER)
DOI10.1177/10497323251365211
PMID40916991
OpenAlexW4414066773
LanguageEN
Citations received3
References cited30

The launch of ChatGPT in November 2022 accelerated discussions and research into whether base large language models (LLMs) could increase the efficiency of qualitative analysis phases or even replace qualitative researchers. Reflexive thematic analysis (RTA) is a commonly used method for qualitative text analysis that emphasizes the researcher's subjectivity and reflexivity to enable a situated, in-depth understanding of knowledge generation. Researchers appear optimistic about the potential of LLMs in qualitative research; however, questions remain about whether base models can meaningfully contribute to the interpretation and abstraction of a dataset. The primary objective of this study was to explore how LLMs may support an RTA of an interview text from health science research. Secondary objectives included identifying recommended prompt strategies for similar studies, highlighting potential weaknesses or challenges, and fostering engagement among qualitative researchers regarding these threats and possibilities. We provided the interview file to an offline LLM and conducted a series of tests aligned with the phases of RTA. Insights from each test guided refinements to the next and contributed to the development of a recommended prompt strategy. At this stage, base LLMs provide limited support and do not increase the efficiency of RTA. At best, LLMs may identify gaps in the researchers' perspectives. Realizing the potential of LLMs to inspire broader discussion and deeper reflections requires a well-defined strategy and the avoidance of misleading prompts, self-referential responses, misguiding translations, and errors. Conclusively, high-quality RTA requires a human, comprehensive familiarization phase, and methodological competence to preserve epistemological integrity

Exploratory research · Photovoice · Qualitative research · Reflexivity · Subjectivity · Thematic analysis · Artificial Intelligence in Healthcare and Education · Clinical Reasoning and Diagnostic Skills · Interpreting and Communication in Healthcare