BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-aspect Sentiment Analysis with Cross-domain Transfer Learning
SN Computer Science · 20.05.2026 · 7 (5)
DOI: 10.1007/s42979-026-05053-x ↗Kurz gefasst
Fachartikel in der Zeitschrift SN Computer Science, online erschienen am 20.05.2026. Verfasst von Ariful Islam und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
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 over 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. It integrates LSTM, BiLSTM, GRU, and BanglaBERT through a theoretically grounded dynamic weighted ensemble for multi-aspect sentiment classification. We introduce a large-scale dataset of 8755 manually annotated Bangla product reviews across four aspects—Quality, Service, Price, and Decoration—collected from major Bangladeshi e-commerce platforms, with a verified inter-annotator agreement of Fleiss’ \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\kappa = 0.821$$\end{document}. Our framework incorporates an integrated explainability suite combining SHAP-based feature attribution and attention mechanism visualization to provide transparent, interpretable insights. Experimental results over five random seeds demonstrate that BanglaSentNet achieves \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$85.0\% \pm 0.6\%$$\end{document} accuracy and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.880 \pm 0.007$$\end{document} F1-score, outperforming standalone deep learning models by 3–7% and traditional machine learning approaches substantially. The explainability components achieve a 9.4/10 interpretability score with 87.6% human evaluation agreement from 18 evaluators. Cross-domain transfer learning experiments reveal robust generalization, with zero-shot performance retaining 67–76% of source domain effectiveness across diverse target domains. Few-shot learning with only 500–1000 samples achieves 90–95% of full fine-tuning performance, significantly reducing annotation costs. This research advances ensemble learning methodologies for low-resource languages and provides actionable, interpretable solutions for Bangla e-commerce platforms.
Zitieren
APA
Islam, A., Hossen, M. R., & Mahmud, T. (2026). BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-aspect Sentiment Analysis with Cross-domain Transfer Learning. SN Computer Science, 7(5). https://doi.org/10.1007/s42979-026-05053-x
Vancouver
Islam A, Hossen MR, Mahmud T. BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-aspect Sentiment Analysis with Cross-domain Transfer Learning. SN Computer Science. 2026;7(5). doi:10.1007/s42979-026-05053-x
BibTeX
@article{Islam2026,
author = {Islam, Ariful and Hossen, Md Rifat and Mahmud, Tanvir},
title = {BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-aspect Sentiment Analysis with Cross-domain Transfer Learning},
journal = {SN Computer Science},
year = {2026},
volume = {7},
number = {5},
doi = {10.1007/s42979-026-05053-x}
}
EUVIMED