Online user generated reviews are now a vital source of product evaluation to both consumer and retailer. There is a need of knowing the factors, generally affecting the helpfulness of reviews and how to identify them. Various studies and researches have been conducted for finding the helpfulness value of online reviews in past recent years. In this paper we have summarized and then analyzed the past work of review helpfulness prediction in a systematic way. The paper provides brief of methodology of each study and how it is contributing towards this domain. It also emphasizes on the pros of the methods used in past and how they are lacking in determining few other aspects of the review helpfulness. The survey discovers that the most popular techniques used for helpfulness prediction are supervised ones and most frequently used are Regression Models and SVM.
1 January 2011 in International Journal of Computer and Electrical Engineering