Saved in:
| Main Authors: | , , |
|---|---|
| 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 |