Sentiment Analysis of Mobile datasets using Naïve Bayes Algorithm

Abstract

Sentiment Analysis is one of the pursued field of Natural Language Processing (NLP). It is an intellectual process of extracting user’s feelings and emotions. The evolution of Internet has driven massive amount of personalized reviews for various related information on the Web specially twitter. These reviews are beneficial for business persons for understanding customer interest, taking better decisions and planning processes. User sentiment refers to the emotions expressed by them through the text reviews. These sentiments can be positive, negative or neutral. The study explores user sentiments and expresses them in terms of user sentiment polarity. Sentiment Analysis poses as a powerful tool for users to extract the needful information, as well as to aggregate the collective sentiments of the reviews. In this paper we present, a lexicon-based approach for sentiment analysis on Twitter. We have used Naïve Bayes algorithm to find sentiment polarities of words in tweeter datasets of some mobile brands. Our approach allows for the detection of sentiment at tweet-level. We evaluate our approach on various mobile brands datasets resulting into accuracy for sentiment polarity classification. We compare various parameters precision, F measure, recall help to improve accuracy.