LLMs in qualitative psychology
Emerging applications of large language models in qualitative psychological research methodology as well as the critics.
Bijker, Rimke et al. (2024)
ChatGPT showed fair-to-strong reliability for assisting qualitative content analysis, especially when building inductive coding schemes.
This study tests whether ChatGPT can reduce the labor involved in qualitative content analysis of online discussions about lowering sugar consumption. Across repeated coding runs, ChatGPT showed stronger agreement for data-driven, inductive coding than for adapting and applying a pre-existing theoretical framework. The results support using an LLM as a potentially useful assistant or second coder, but emphasize that researchers must iteratively evaluate reliability at every stage of the analysis.
The study used prompt-engineered ChatGPT conversations to extract and code behavior-change mechanisms in 537 forum posts, comparing outputs across inductive and theory-guided schemes.
Basic knowledge of qualitative content analysis, coding reliability, and behavior-change frameworks is helpful.
Quantifies coding results
— ES