Saved in:
Bibliographic Details
Main Authors: Flanders, Samuel, Nungsari, Melati, Loong, Mark Cheong Wing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.08213
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913788631973888
author Flanders, Samuel
Nungsari, Melati
Loong, Mark Cheong Wing
author_facet Flanders, Samuel
Nungsari, Melati
Loong, Mark Cheong Wing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Big Meaning: Qualitative Analysis on Large Bodies of Data Using AI
Flanders, Samuel
Nungsari, Melati
Loong, Mark Cheong Wing
Computation and Language
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.
title Big Meaning: Qualitative Analysis on Large Bodies of Data Using AI
topic Computation and Language
url https://arxiv.org/abs/2504.08213