Identifying Emerging Concepts in Large Corpora
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910851034775552 |
|---|---|
| author | Ma, Sibo Nyarko, Julian |
| author_facet | Ma, Sibo Nyarko, Julian |
| contents | We introduce a new method to identify emerging concepts in large text corpora. By analyzing changes in the heatmaps of the underlying embedding space, we are able to detect these concepts with high accuracy shortly after they originate, in turn outperforming common alternatives. We further demonstrate the utility of our approach by analyzing speeches in the U.S. Senate from 1941 to 2015. Our results suggest that the minority party is more active in introducing new concepts into the Senate discourse. We also identify specific concepts that closely correlate with the Senators' racial, ethnic, and gender identities. An implementation of our method is publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_21315 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Identifying Emerging Concepts in Large Corpora Ma, Sibo Nyarko, Julian Computation and Language Computers and Society We introduce a new method to identify emerging concepts in large text corpora. By analyzing changes in the heatmaps of the underlying embedding space, we are able to detect these concepts with high accuracy shortly after they originate, in turn outperforming common alternatives. We further demonstrate the utility of our approach by analyzing speeches in the U.S. Senate from 1941 to 2015. Our results suggest that the minority party is more active in introducing new concepts into the Senate discourse. We also identify specific concepts that closely correlate with the Senators' racial, ethnic, and gender identities. An implementation of our method is publicly available. |
| title | Identifying Emerging Concepts in Large Corpora |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2502.21315 |