# Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content

arXiv: https://arxiv.org/abs/2504.13545 · HTML: https://mlsanity.com/paper/2504.13545/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [FinBERT: A Pretrained Language Model for Financial Communications](https://mlsanity.com/paper/2006.08097/) (2020)
- [SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning](https://mlsanity.com/paper/2307.10234/) (2023)
- [Sentiment Analysis for Sinhala Language using Deep Learning Techniques](https://mlsanity.com/paper/2011.07280/) (2020)
- [Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content](https://mlsanity.com/paper/2504.10679/) (2025)

## Built on by (most cited first, 3 of 3)

- [SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language](https://mlsanity.com/paper/2510.22160/) (2025)
- [Privacy Preserving Topic-wise Sentiment Analysis of the Iran Israel USA Conflict Using Federated Transformer Models](https://mlsanity.com/paper/2603.13655/) (2026)
- [Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass Distribution for Deep Learning Biomass Estimation](https://mlsanity.com/paper/2607.05260/) (2026)

## Abstract (arXiv)

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.