Detection and summarization of genuine review using Visual Data Mining

Abstract

In earlier days we were asking our friends or relatives for their opinions regarding products which we want to purchase from the merchants. But now a day's E-commerce is gaining more and more popularity. Whatever query we are having, we can find its answer from World Wide Web. Merchants are also selling their products online and at a same time they are asking customer's review regarding products, which customer has bought. This would be beneficial to merchants as well as customers also. As the numbers of customers are growing, reviews received by products are also growing in large amount. Thus, mining opinions from product reviews is an important research topic. However, existing research is more focused towards classification and summarization of such online opinions. An important issue related to the trustworthiness of online opinions has been neglected most often. There is no reported study on assessing the trustworthiness of reviews. This research paper aims to first classify the opinion (positive or negative) carried out by detection of a review(spam or a nonspam) based on rating behavior and finally removing spam reviews, which provides a trusted review to help the customer in taking appropriate buying decision. This paper proposes a novel and effective technique, which will represent classified opinion in form of "chernoff face".