BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning
Ariful Islam, Md Rifat Hossen, Tanvir Mahmud
TL;DR
BanglaSentNet tackles multi-aspect sentiment analysis in Bangla e-commerce reviews under data scarcity and domain shift by introducing an explainable hybrid ensemble that integrates BanglaBERT with LSTM-based architectures. It couples an 8,755-entry annotated dataset with SHAP and attention-based explanations to ensure transparency and trust, and demonstrates cross-domain transfer learning with zero-shot and few-shot protocols across diverse domains. The approach achieves state-of-the-art performance (85% accuracy, 0.88 F1) and shows robust generalization, including practical deployments for pricing and service improvements. The work also provides a comprehensive explainability framework and actionable guidelines for deploying interpretable, cross-domain sentiment analytics in low-resource settings.
Abstract
Multi-aspect sentiment analysis of Bangla e-commerce reviews remains challenging due to limited annotated datasets, morphological complexity, code-mixing phenomena, and domain shift issues, affecting 300 million Bangla-speaking users. Existing approaches lack explainability and cross-domain generalization capabilities crucial for practical deployment. We present BanglaSentNet, an explainable hybrid deep learning framework integrating LSTM, BiLSTM, GRU, and BanglaBERT through dynamic weighted ensemble learning for multi-aspect sentiment classification. We introduce a dataset of 8,755 manually annotated Bangla product reviews across four aspects (Quality, Service, Price, Decoration) from major Bangladeshi e-commerce platforms. Our framework incorporates SHAP-based feature attribution and attention visualization for transparent insights. BanglaSentNet achieves 85% accuracy and 0.88 F1-score, outperforming standalone deep learning models by 3-7% and traditional approaches substantially. The explainability suite achieves 9.4/10 interpretability score with 87.6% human agreement. Cross-domain transfer learning experiments reveal robust generalization: zero-shot performance retains 67-76% effectiveness across diverse domains (BanglaBook reviews, social media, general e-commerce, news headlines); few-shot learning with 500-1000 samples achieves 90-95% of full fine-tuning performance, significantly reducing annotation costs. Real-world deployment demonstrates practical utility for Bangladeshi e-commerce platforms, enabling data-driven decision-making for pricing optimization, service improvement, and customer experience enhancement. This research establishes a new state-of-the-art benchmark for Bangla sentiment analysis, advances ensemble learning methodologies for low-resource languages, and provides actionable solutions for commercial applications.