The SAFE miner: A fine grained aspect level approach for resolving the sentiment

Sentiment analysis is the study of classifying human´s sentiments, evaluations, attitudes, opinions about some topic, expressed in form of text or speech. In order to improve the customer satisfaction, many e-commerce sites provides the provision to write reviews about products. Instead of manually reading and evaluating numerous reviews, an automated procedure can be deployed to get the overall polarity of the reviews. The goal of the research is to present an approach with the target of deriving qualitative sentiment analysis. Although many techniques have been proposed by the researchers for extracting sentiments from text. This paper introduces the SAFE (sentiment analysis and feature extraction) miner, a fine grained approach for calculating the sentiment score at aspect level. Thus, developing the feature extraction matrix (FEM). FEM will help in determining the features, being commented upon. It will also help in detecting the popular features among the reviews. The paper aims at mining sentiment for each product review and overall sentiment score associated with each product review. The efficient ranking of the features will be deduced, based on the opinions.