Sentiment analysis in Bengali via transfer learning using multi-lingual BERT
This work provides the first publicly available manually tagged sentiment analysis datasets and a competitive model for Bengali, a language with significant inflectional complexity and a lack of resources, benefiting researchers and applications in this domain.
This paper tackles sentiment analysis in Bengali, a highly inflected Indo-Aryan language, by creating new 2-class and 3-class manually tagged datasets. They fine-tuned a multi-lingual BERT model using transfer learning, achieving 71% accuracy for 2-class classification, surpassing the previous state-of-the-art of 68%, and 60% accuracy for the 3-class classification.
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.