Sentiment Analysis and Review Classification using Deep Learning

Abstract

Sentiment analysis or opinion mining is the method of deciding the emotions, opinions behind series of words, its accustomed gain an understanding of the attitudes, opinions and emotions expressed by the people. In recent years, research work is being performed in these fields by applying numerous methodologies. Sentiment analysis of social media content has become one of the most sought area among researchers because the number of product review sites, social networking sites, blogs, and forums are developing extensively. This field mainly utilizes supervised, unsupervised and semi-supervised technique for this sentiment prediction and classification task. This project studies the inability of widely used feature selection method like Information gain (IG) on machine learning and deep learning approaches. Initially, feature selection method called information gain has been used to select the feature subsets. In addition Naïve Bayes classification is done to find the probability of features found in all sub categories of reviews. Deep learning approach has been used in exact classification of new review from the given dataset and R language is used to develop the application.