Enhancing Financial Sentiment Analysis with Expert-Designed Hint
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914957665239040 |
|---|---|
| author | Chen, Chung-Chi Takamura, Hiroya Kobayashi, Ichiro Miyao, Yusuke |
| author_facet | Chen, Chung-Chi Takamura, Hiroya Kobayashi, Ichiro Miyao, Yusuke |
| contents | This paper investigates the role of expert-designed hint in enhancing sentiment analysis on financial social media posts. We explore the capability of large language models (LLMs) to empathize with writer perspectives and analyze sentiments. Our findings reveal that expert-designed hint, i.e., pointing out the importance of numbers, significantly improve performances across various LLMs, particularly in cases requiring perspective-taking skills. Further analysis on tweets containing different types of numerical data demonstrates that the inclusion of expert-designed hint leads to notable improvements in sentiment analysis performance, especially for tweets with monetary-related numbers. Our findings contribute to the ongoing discussion on the applicability of Theory of Mind in NLP and open new avenues for improving sentiment analysis in financial domains through the strategic use of expert knowledge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17448 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Financial Sentiment Analysis with Expert-Designed Hint Chen, Chung-Chi Takamura, Hiroya Kobayashi, Ichiro Miyao, Yusuke Computation and Language This paper investigates the role of expert-designed hint in enhancing sentiment analysis on financial social media posts. We explore the capability of large language models (LLMs) to empathize with writer perspectives and analyze sentiments. Our findings reveal that expert-designed hint, i.e., pointing out the importance of numbers, significantly improve performances across various LLMs, particularly in cases requiring perspective-taking skills. Further analysis on tweets containing different types of numerical data demonstrates that the inclusion of expert-designed hint leads to notable improvements in sentiment analysis performance, especially for tweets with monetary-related numbers. Our findings contribute to the ongoing discussion on the applicability of Theory of Mind in NLP and open new avenues for improving sentiment analysis in financial domains through the strategic use of expert knowledge. |
| title | Enhancing Financial Sentiment Analysis with Expert-Designed Hint |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.17448 |