A Systematic Review of Sentiment Analysis from Bengali Text using NLP

Abstract

Sentiment Analysis (SA) is the method of studying a person’s comments and statements through computational means. It is a sub-domain of Natural Language Processing. A sentiment analysis (SA) system is created by training a significant number of positive, negative or neutral sentence datasets. Although there are many research papers on this subject in English, the work of sentiment analysis in Bengali has not become very popular due to the complexity of the Bangla language and the insufficient presence of the Bangla language online. But now the use of Bengali language has increased in online news, social media, and blogs. At the same time, the number of researches on Bengali NLP is also increasing. But what is the current state of sentiment analysis, its limitations and is there still room for improvement in some places, are not being properly reviewed and research is lagging behind. We have conducted a review on sentiment analysis so that future researchers of sentiment analysis can easily find out about the current state of sentiment analysis. In this research, we have tried to survey the current context of sentiment analysis (SA) and at the same time, we have created a sequence of comparatively better research from the existing ones. To create this sequence we followed a method called is TOPSIS. We have also discussed the challenges to overcome for improving the Sentiment analyzer.