Divide (Text) and Conquer (Sentiment): Improved Sentiment Classification by Constituent Conflict Resolution
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_ | 1866910935607672832 |
|---|---|
| author | Kościałkowski, Jan Marcinkowski, Paweł |
| author_facet | Kościałkowski, Jan Marcinkowski, Paweł |
| contents | Sentiment classification, a complex task in natural language processing, becomes even more challenging when analyzing passages with multiple conflicting tones. Typically, longer passages exacerbate this issue, leading to decreased model performance. The aim of this paper is to introduce novel methodologies for isolating conflicting sentiments and aggregating them to effectively predict the overall sentiment of such passages. One of the aggregation strategies involves a Multi-Layer Perceptron (MLP) model which outperforms baseline models across various datasets, including Amazon, Twitter, and SST while costing $\sim$1/100 of what fine-tuning the baseline would take. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06320 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Divide (Text) and Conquer (Sentiment): Improved Sentiment Classification by Constituent Conflict Resolution Kościałkowski, Jan Marcinkowski, Paweł Machine Learning Artificial Intelligence Computation and Language Sentiment classification, a complex task in natural language processing, becomes even more challenging when analyzing passages with multiple conflicting tones. Typically, longer passages exacerbate this issue, leading to decreased model performance. The aim of this paper is to introduce novel methodologies for isolating conflicting sentiments and aggregating them to effectively predict the overall sentiment of such passages. One of the aggregation strategies involves a Multi-Layer Perceptron (MLP) model which outperforms baseline models across various datasets, including Amazon, Twitter, and SST while costing $\sim$1/100 of what fine-tuning the baseline would take. |
| title | Divide (Text) and Conquer (Sentiment): Improved Sentiment Classification by Constituent Conflict Resolution |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.06320 |