Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.18919 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913058185543680 |
|---|---|
| author | Yoshida, Yura Kanai, Masato Nakayama, Masataka Ohsawa, Haruki Uchida, Yukiko Yuminaga, Arata Hoshina, Gakuse Sayama, Nobuo |
| author_facet | Yoshida, Yura Kanai, Masato Nakayama, Masataka Ohsawa, Haruki Uchida, Yukiko Yuminaga, Arata Hoshina, Gakuse Sayama, Nobuo |
| contents | Analyzing topics extracted from text data in relation to external outcomes is important across fields such as computational social science and organizational research. However, existing topic modeling methods struggle to simultaneously achieve interpretability, topic specificity (alignment with concrete actions or characteristics), and polarity stance consistency (absence of mixed positive and negative evaluations within a topic). Focusing on leadership analysis using corporate review data, this study proposes a method leveraging large language models to generate topics that satisfy these properties, along with an evaluation framework tailored to external outcome analysis. The framework explicitly incorporates topic specificity and polarity stance consistency as evaluation criteria and examines automated evaluation methods based on existing metrics. Using employee reviews from OpenWork, a major corporate review platform in Japan, the proposed method achieves improved interpretability, specificity, and polarity consistency compared to existing approaches. In analyses of external outcomes such as employee morale, it also produces topics with higher explanatory power. These results suggest that the proposed method and evaluation framework provide a generalized approach for topic analysis in applications involving external outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18919 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Proposing Topic Models and Evaluation Frameworks for Analyzing Associations with External Outcomes: An Application to Leadership Analysis Using Large-Scale Corporate Review Data Yoshida, Yura Kanai, Masato Nakayama, Masataka Ohsawa, Haruki Uchida, Yukiko Yuminaga, Arata Hoshina, Gakuse Sayama, Nobuo Computation and Language Analyzing topics extracted from text data in relation to external outcomes is important across fields such as computational social science and organizational research. However, existing topic modeling methods struggle to simultaneously achieve interpretability, topic specificity (alignment with concrete actions or characteristics), and polarity stance consistency (absence of mixed positive and negative evaluations within a topic). Focusing on leadership analysis using corporate review data, this study proposes a method leveraging large language models to generate topics that satisfy these properties, along with an evaluation framework tailored to external outcome analysis. The framework explicitly incorporates topic specificity and polarity stance consistency as evaluation criteria and examines automated evaluation methods based on existing metrics. Using employee reviews from OpenWork, a major corporate review platform in Japan, the proposed method achieves improved interpretability, specificity, and polarity consistency compared to existing approaches. In analyses of external outcomes such as employee morale, it also produces topics with higher explanatory power. These results suggest that the proposed method and evaluation framework provide a generalized approach for topic analysis in applications involving external outcomes. |
| title | Proposing Topic Models and Evaluation Frameworks for Analyzing Associations with External Outcomes: An Application to Leadership Analysis Using Large-Scale Corporate Review Data |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.18919 |