Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918012334899200 |
|---|---|
| author | Miriyala, Vihaan Bukkapatnam, Smrithi Prahallad, Lavanya |
| author_facet | Miriyala, Vihaan Bukkapatnam, Smrithi Prahallad, Lavanya |
| contents | We explore the use of Chain-of-Thought (CoT) prompting with large language models (LLMs) to improve the accuracy of granular sentiment categorization in app store reviews. Traditional numeric and polarity-based ratings often fail to capture the nuanced sentiment embedded in user feedback. We evaluated the effectiveness of CoT prompting versus simple prompting on 2000 Amazon app reviews by comparing each method's predictions to human judgements. CoT prompting improved classification accuracy from 84% to 93% highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models Miriyala, Vihaan Bukkapatnam, Smrithi Prahallad, Lavanya Computation and Language Machine Learning We explore the use of Chain-of-Thought (CoT) prompting with large language models (LLMs) to improve the accuracy of granular sentiment categorization in app store reviews. Traditional numeric and polarity-based ratings often fail to capture the nuanced sentiment embedded in user feedback. We evaluated the effectiveness of CoT prompting versus simple prompting on 2000 Amazon app reviews by comparing each method's predictions to human judgements. CoT prompting improved classification accuracy from 84% to 93% highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance. |
| title | Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2505.04135 |