Big Meaning: Qualitative Analysis on Large Bodies of Data Using AI
This addresses the challenge for qualitative researchers in analyzing large datasets by providing an incremental tool to prioritize documents for human coding.
The study tackled the problem of efficiently identifying texts with high qualitative insight potential in thematic analysis by using AI-generated codes as a proxy for fecundity, resulting in AI-selected texts showing approximately twice the fecundity compared to random selection.
This study introduces a framework that leverages AI-generated descriptive codes to indicate a text's fecundity--the density of unique human-generated codes--in thematic analysis. Rather than replacing human interpretation, AI-generated codes guide the selection of texts likely to yield richer qualitative insights. Using a dataset of 2,530 Malaysian news articles on refugee attitudes, we compare AI-selected documents to randomly chosen ones by having three human coders independently derive codes. The results demonstrate that AI-selected texts exhibit approximately twice the fecundity. Our findings support the use of AI-generated codes as an effective proxy for identifying documents with a high potential for meaning-making in thematic analysis.