Sentiment Analysis on Bangla Conversation Data Using Machine Learning Approach

Abstract

This research titled “Sentiment Analysis on Bangla Conversation Data Using Machine Learning Approach” is from conversations people's sentiment during the conversation period can be extracted as valuable information. In the field of NLP, text analysis and conclusion of any information as summarization can be done by Sentiment Analysis. The necessity of sentiment analysis of a conversation is increasing because of the use of conversation for customer support portal in many e-commerce platforms and crime investigations on digital evidence. Other languages, like English have enriched libraries and resources for natural language processing but there are very few works done over Bangla language. Because of the grammatical complexity in Bangla language, it is more difficult to extract sentiments from Bangla conversation data. That's why it opens the door of huge scopes of research. A machine learning approach was applied to extract sentiment from Bangla conversation. For that, Support Vector Machine, Multinomial Naïve Bayes, K-Nearest Neighbors, Logistic Regression, Decision Tree & Random Forest was used. From the dataset, extracted information was labeled as Positive and Negative.