# Sentiment analysis in Bengali via transfer learning using multi-lingual BERT

arXiv: https://arxiv.org/abs/2012.07538 · HTML: https://mlsanity.com/paper/2012.07538/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 11 of 11)

- [BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews](https://mlsanity.com/paper/2305.06595/) (2023)
- [SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and its Evaluation](https://mlsanity.com/paper/2306.06147/) (2023)
- [A Comparative Analysis of Noise Reduction Methods in Sentiment Analysis on Noisy Bangla Texts](https://mlsanity.com/paper/2401.14360/) (2024)
- [MONOVAB : An Annotated Corpus for Bangla Multi-label Emotion Detection](https://mlsanity.com/paper/2309.15670/) (2023)
- [nlpBDpatriots at BLP-2023 Task 2: A Transfer Learning Approach to Bangla Sentiment Analysis](https://mlsanity.com/paper/2311.15032/) (2023)
- [RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers](https://mlsanity.com/paper/2310.14261/) (2023)
- [KuBERT: Central Kurdish BERT Model and Its Application for Sentiment Analysis](https://mlsanity.com/paper/2509.16804/) (2025)
- [BanglaNLP at BLP-2023 Task 2: Benchmarking different Transformer Models for Sentiment Analysis of Bangla Social Media Posts](https://mlsanity.com/paper/2310.09238/) (2023)
- [Securing Social Spaces: Harnessing Deep Learning to Eradicate Cyberbullying](https://mlsanity.com/paper/2404.03686/) (2024)
- [BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning](https://mlsanity.com/paper/2511.23264/) (2025)
- [Two-Stage Bengali Sentiment Classification: Domain Adaptation Through Continual Learning and Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2608.01471/) (2026)

## Abstract (arXiv)

Sentiment analysis (SA) in Bengali is challenging due to this Indo-Aryan language's highly inflected properties with more than 160 different inflected forms for verbs and 36 different forms for noun and 24 different forms for pronouns. The lack of standard labeled datasets in the Bengali domain makes the task of SA even harder. In this paper, we present manually tagged 2-class and 3-class SA datasets in Bengali. We also demonstrate that the multi-lingual BERT model with relevant extensions can be trained via the approach of transfer learning over those novel datasets to improve the state-of-the-art performance in sentiment classification tasks. This deep learning model achieves an accuracy of 71% for 2-class sentiment classification compared to the current state-of-the-art accuracy of 68%. We also present the very first Bengali SA classifier for the 3-class manually tagged dataset, and our proposed model achieves an accuracy of 60%. We further use this model to analyze the sentiment of public comments in the online daily newspaper. Our analysis shows that people post negative comments for political or sports news more often, while the religious article comments represent positive sentiment. The dataset and code is publicly available at https://github.com/KhondokerIslam/BengaliSentiment.