Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12099 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915936073678848 |
|---|---|
| author | Rangreji, Sandesh S Zhong, Mian Field, Anjalie |
| author_facet | Rangreji, Sandesh S Zhong, Mian Field, Anjalie |
| contents | Analyses of document collections often require selecting what data to analyze, as not all documents are relevant to a particular research question and computational constraints preclude analyzing all documents, yet little work has examined effects of selection strategy choices. We systematically evaluate seven selection methods (from random selection to hybrid retrieval) on outputs from four text analyses methods (LDA, BERTopic, TopicGPT, HiCode) over two datasets with 26 open-ended queries. Our evaluation reveals practice guidance: semantic or hybrid retrieval offer strong go-to approaches that avoid the pitfalls of weaker selection strategies and the unnecessary compute overhead of more complicated ones. Overall, our evaluation framework establishes data selection as a methodological decision, rather than a practical necessity, inviting the development of new strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12099 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Effect of Document Selection on Query-focused Text Analysis Rangreji, Sandesh S Zhong, Mian Field, Anjalie Information Retrieval Computation and Language Analyses of document collections often require selecting what data to analyze, as not all documents are relevant to a particular research question and computational constraints preclude analyzing all documents, yet little work has examined effects of selection strategy choices. We systematically evaluate seven selection methods (from random selection to hybrid retrieval) on outputs from four text analyses methods (LDA, BERTopic, TopicGPT, HiCode) over two datasets with 26 open-ended queries. Our evaluation reveals practice guidance: semantic or hybrid retrieval offer strong go-to approaches that avoid the pitfalls of weaker selection strategies and the unnecessary compute overhead of more complicated ones. Overall, our evaluation framework establishes data selection as a methodological decision, rather than a practical necessity, inviting the development of new strategies. |
| title | The Effect of Document Selection on Query-focused Text Analysis |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2604.12099 |