Skip to main content
All Reviews
PsychologyNiche
intermediate

ChatGPT for Automated Qualitative Research: Content Analysis

Bijker, Rimke et al. (2024)

Published
Jul 25, 2024
Journal
Journal of Medical Internet Research · Vol. 26
DOI
10.2196/59050

At a GlanceAI

ChatGPT showed fair-to-strong reliability for assisting qualitative content analysis, especially when building inductive coding schemes.

SummaryAI

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.

Method SnapshotAI

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.

BackgroundAI

Basic knowledge of qualitative content analysis, coding reliability, and behavior-change frameworks is helpful.

Quantifies coding results

ES

Expert Review: ChatGPT for Automated Qualitative Research: Content Analysis | Marginalia