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

TL;DR

This paper introduces new Bengali sentiment analysis datasets and demonstrates that transfer learning with multi-lingual BERT improves sentiment classification accuracy in Bengali, a low-resource language.

Contribution

The paper presents the first Bengali sentiment analysis datasets and applies transfer learning with multi-lingual BERT to enhance classification performance.

Findings

Achieved 71% accuracy for 2-class sentiment classification.

First Bengali 3-class sentiment classifier with 60% accuracy.

Analyzed public comments showing sentiment trends in news articles.

Abstract

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/Bengali\_Sentiment.