A Novel Ranking Technique for Opinion Search

Abstract

With the continuously increasing volume of e-commerce transactions, it is now very common to buy some products and to evaluate them on the World Wide Web. The product reviews are very useful to customers because they can make better decisions based on the indirect; experiences obtainable through these reviews. However, as the number of reviews increases, it is impossible for users to read all the relevant review documents. In order to alleviate this problem, there has been active research on ways to effectively search review data. The opinion search is different from the general web search in terms of ranking strategy. This is because customers tend to mainly find out subjective opinions rather than objective statements such as product information. In this paper, we propose a novel ranking method that can reflect user's intention by using opinion mining techniques. The proposed method analyzes product reviews with not only keyword matching but also the degree of subjective opinions. Through extensive experiments, we show that our proposed method outperforms conventional ones.