Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content
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_ | 1866909584174612480 |
|---|---|
| author | Rizvi, Azmarah Thamindu, Navojith Adhikari, A. M. N. H. Senevirathna, W. P. U. Kasthurirathna, Dharshana Abeywardhana, Lakmini |
| author_facet | Rizvi, Azmarah Thamindu, Navojith Adhikari, A. M. N. H. Senevirathna, W. P. U. Kasthurirathna, Dharshana Abeywardhana, Lakmini |
| contents | Sentiment analysis is crucial for brand reputation management in the banking sector, where customer feedback spans English, Sinhala, Singlish, and code-mixed text. Existing models struggle with low-resource languages like Sinhala and lack interpretability for practical use. This research develops a hybrid aspect-based sentiment analysis framework that enhances multilingual capabilities with explainable outputs. Using cleaned banking customer reviews, we fine-tune XLM-RoBERTa for Sinhala and code-mixed text, integrate domain-specific lexicon correction, and employ BERT-base-uncased for English. The system classifies sentiment (positive, neutral, negative) with confidence scores, while SHAP and LIME improve interpretability by providing real-time sentiment explanations. Experimental results show that our approaches outperform traditional transformer-based classifiers, achieving 92.3 percent accuracy and an F1-score of 0.89 in English and 88.4 percent in Sinhala and code-mixed content. An explainability analysis reveals key sentiment drivers, improving trust and transparency. A user-friendly interface delivers aspect-wise sentiment insights, ensuring accessibility for businesses. This research contributes to robust, transparent sentiment analysis for financial applications by bridging gaps in multilingual, low-resource NLP and explainability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content Rizvi, Azmarah Thamindu, Navojith Adhikari, A. M. N. H. Senevirathna, W. P. U. Kasthurirathna, Dharshana Abeywardhana, Lakmini Computation and Language Artificial Intelligence Machine Learning Sentiment analysis is crucial for brand reputation management in the banking sector, where customer feedback spans English, Sinhala, Singlish, and code-mixed text. Existing models struggle with low-resource languages like Sinhala and lack interpretability for practical use. This research develops a hybrid aspect-based sentiment analysis framework that enhances multilingual capabilities with explainable outputs. Using cleaned banking customer reviews, we fine-tune XLM-RoBERTa for Sinhala and code-mixed text, integrate domain-specific lexicon correction, and employ BERT-base-uncased for English. The system classifies sentiment (positive, neutral, negative) with confidence scores, while SHAP and LIME improve interpretability by providing real-time sentiment explanations. Experimental results show that our approaches outperform traditional transformer-based classifiers, achieving 92.3 percent accuracy and an F1-score of 0.89 in English and 88.4 percent in Sinhala and code-mixed content. An explainability analysis reveals key sentiment drivers, improving trust and transparency. A user-friendly interface delivers aspect-wise sentiment insights, ensuring accessibility for businesses. This research contributes to robust, transparent sentiment analysis for financial applications by bridging gaps in multilingual, low-resource NLP and explainability. |
| title | Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.13545 |