Helping e-commerce consumers make good purchase decisions: A user reviews-based approach

Abstract

Online product reviews provided by the consumers, who have previously purchased and used some particular products, form a rich source of information for other consumers who would like to study about these products in order to make their purchase decisions. Realizing this great need of consumers, several e-commerce web sites such as Amazon.com offer facilities for consumers to review products and exchange their purchase opinions. Unfortunately, reading through the massive amounts of product reviews available online from many e-communities, forums and newsgroups is not only a tedious task but also an impossible one. Indeed, nowadays consumers need an effective and reliable method to search through those huge sources of information and sort out the most appropriate and helpful product reviews. This paper proposes a model to discover the helpfulness of online product reviews. Product reviews can be analyzed and ranked by our scoring system and those reviews that may help consumers better than others will be found. In addition, we compare our model with a number of machine learning techniques. Our experimental results confirm that our approach is effective in ranking and classifying online product reviews. © 2009 Springer Berlin Heidelberg.