Analyzing Emotions in Bangla Social Media Comments Using Machine Learning and LIME

2025-06-11

AI Summary

This work addresses the challenge of sentiment analysis for low-resource, regionally and culturally rich Bengali social media text. We propose a hybrid multi-model system integrating traditional machine learning and deep learning, evaluated on the EmoNoBa dataset (22,698 comments). Methodologically, we introduce the first integration of LIME with AdaBoost decision trees to enable fine-grained, interpretable predictions; design a collaborative BiLSTM–AdaBoost modeling framework to enhance representation learning for low-resource languages; and empirically validate PCA’s effectiveness in reducing dimensionality of TF-IDF + n-gram features. Results demonstrate that the AdaBoost+LIME approach maintains high accuracy while substantially improving model transparency and debuggability. Our framework delivers a reproducible, interpretable technical pathway for sentiment analysis in low-resource languages, advancing both practical applicability and analytical rigor in culturally nuanced NLP tasks.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Evaluation and Analysis
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Research on understanding emotions in written language continues to expand, especially for understudied languages with distinctive regional expressions and cultural features, such as Bangla. This study examines emotion analysis using 22,698 social media comments from the EmoNoBa dataset. For language analysis, we employ machine learning models: Linear SVM, KNN, and Random Forest with n-gram data from a TF-IDF vectorizer. We additionally investigated how PCA affects the reduction of dimensionality. Moreover, we utilized a BiLSTM model and AdaBoost to improve decision trees. To make our machine learning models easier to understand, we used LIME to explain the predictions of the AdaBoost classifier, which uses decision trees. With the goal of advancing sentiment analysis in languages with limited resources, our work examines various techniques to find efficient techniques for emotion identification in Bangla.

Problem

• Analyzing emotions in Bangla social media comments using machine learning
• Exploring efficient techniques for emotion identification in understudied languages
• Improving model interpretability with LIME for AdaBoost classifier predictions

Innovation

• Machine learning models for Bangla emotion analysis
• BiLSTM and AdaBoost to enhance decision trees
• LIME for explaining AdaBoost classifier predictions