Opinion mining using Naïve Bayes

The opinion of other person is an important information for decision making. People share useful information to others as the growth of social media through Internet. This information is used to organize, explore and analyze for better decision making. Opinion Mining is a Natural Language Processing task which aims to determine the attitude of a person by identifying and extracting information. The major task in opinion mining is to classify the polarity of a review at sentence level, whether the expressed opinion is positive or negative. In this paper, we design a classifier using Naïve Bayes as a machine learning approach to determine the opinion expressed both in English and Bangla. We label the polarity of each opinion as weak, steady and strong. The performances are evaluated and the comparative results are analyzed.