Big Meaning: Qualitative Analysis on Large Bodies of Data Using AI

2025/04/11 by Flanders, Samuel, Nungsari, Melati, Loong, Mark Cheong Wing · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2504.08213

Abstract

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.

Cited by

• Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale

Related

• Large Language Models and Thematic Analysis: Human-AI Synergy in Researching Hate Speech on Social Media
• Opening Up to Big Data : Computer-Assisted Analysis of Textual Data in Social Sciences
• Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks
• Artificial Intelligence to Support Qualitative Data Analysis: Promises, Approaches, Pitfalls
• Exploring the Use of AI in Qualitative Data Analysis: Comparing Manual Processing with Avidnote for Theme Generation