# Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content

arXiv: https://arxiv.org/abs/2504.10679 · HTML: https://mlsanity.com/paper/2504.10679/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 14 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 1 of 1)

- [MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction](https://mlsanity.com/paper/2110.06651/) (2021)

## Built on by (most cited first, 2 of 2)

- [Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content](https://mlsanity.com/paper/2504.13545/) (2025)
- [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)

Brand reputation in the banking sector is maintained through insightful analysis of customer opinion on code-mixed and multilingual content. Conventional NLP models misclassify or ignore code-mixed text, when mix with low resource languages such as Sinhala-English and fail to capture domain-specific knowledge. This study introduces a hybrid NLP method to improve keyword extraction, content filtering, and aspect-based classification of banking content. Keyword extraction in English is performed with a hybrid approach comprising a fine-tuned SpaCy NER model, FinBERT-based KeyBERT embeddings, YAKE, and EmbedRank, which results in a combined accuracy of 91.2%. Code-mixed and Sinhala keywords are extracted using a fine-tuned XLM-RoBERTa model integrated with a domain-specific Sinhala financial vocabulary, and it results in an accuracy of 87.4%. To ensure data quality, irrelevant comment filtering was performed using several models, with the BERT-base-uncased model achieving 85.2% for English and XLM-RoBERTa 88.1% for Sinhala, which was better than GPT-4o, SVM, and keyword-based filtering. Aspect classification followed the same pattern, with the BERT-base-uncased model achieving 87.4% for English and XLM-RoBERTa 85.9% for Sinhala, both exceeding GPT-4 and keyword-based approaches. These findings confirm that fine-tuned transformer models outperform traditional methods in multilingual financial text analysis. The present framework offers an accurate and scalable solution for brand reputation monitoring in code-mixed and low-resource banking environments.