Online Product Reviews Based on Sentiment Analysis

Abstract

With the speedy growth of social media on the web, there is a growing amount of information posted to social online services in an audio format, audiovisual format, and textual format in the form of reviews, and comments. People are sharing their views and opinions online. With the rising availability of review sites and blogs, consumers depend on online reviews to make their purchase decisions. A survey found that more than 90% of consumers read online reviews, to judge purchasing decision on consumer products. The sentiment analysis (SA) can be achieved by performing analysis at various levels of the granularity-document level, sentence level, phrase level, and feature level. In this paper, online reviews can be filtered using the SA and repeated incremental pruning to produce error reduction algorithm is presented.