Conducting thematic analysis in qualitative research can be laborious and time-consuming.We propose and evaluate the feasibility of using Generative Pre-trained Transformer(GPT)models to assist public health researche...Conducting thematic analysis in qualitative research can be laborious and time-consuming.We propose and evaluate the feasibility of using Generative Pre-trained Transformer(GPT)models to assist public health researchers in extracting themes from interview transcripts.Carefully engineered prompts were used to sequentially extract and synthesize transcripts into a concise set of study-level themes relevant to the study’s goals.An evaluation using a 5-point Likert scale(0−4)assessed GPTgenerated themes across 11 published studies based on four criteria:succinctness,alignment with researcher-identified themes,quality of explanations,and relevance of quotes.Across all four criteria,the scores averaged 3.05(95%Confidence Interval(CI):[2.93,3.16]).Our findings indicate that at least half of the GPT-generated themes align with those in published studies,exhibiting succinctness with minimal repetition,substantial depth of explanations,and relevant quotations.Despite these promising results,practices such as complementing outputs with field-specific knowledge are recommended.展开更多
基金supported in part by the Washington University Center for Diabetes Translation Research(WU-CDTR)under Grant Number P30DK092950 from the National Institute of Diabetes and Digestive and Kidney Diseases(NIDDK)。
文摘Conducting thematic analysis in qualitative research can be laborious and time-consuming.We propose and evaluate the feasibility of using Generative Pre-trained Transformer(GPT)models to assist public health researchers in extracting themes from interview transcripts.Carefully engineered prompts were used to sequentially extract and synthesize transcripts into a concise set of study-level themes relevant to the study’s goals.An evaluation using a 5-point Likert scale(0−4)assessed GPTgenerated themes across 11 published studies based on four criteria:succinctness,alignment with researcher-identified themes,quality of explanations,and relevance of quotes.Across all four criteria,the scores averaged 3.05(95%Confidence Interval(CI):[2.93,3.16]).Our findings indicate that at least half of the GPT-generated themes align with those in published studies,exhibiting succinctness with minimal repetition,substantial depth of explanations,and relevant quotations.Despite these promising results,practices such as complementing outputs with field-specific knowledge are recommended.
