Richong Zhang, Thomas Tran
Most E-commerce web sites and online communities provide interfaces and platforms for consumers to express their opinions about a specific product by writing personal reviews. The fast development of E-commerce has caused such a huge amount of online product reviews to become available to consumers that it is impossible for potential consumers to read through all the reviews and to make a quick purchasing decision. Review readers are asked to vote if a review is “Helpful” or “Unhelpful” and the most positively voted reviews are placed on the top of product review list. However, the accumulation of votes takes time for a review to be fully voted and newly published reviews are always listed at the bottom of the review list. This paper proposes a linear model to predict the helpfulness of online product reviews. Reviews can be quickly ranked and classified by our model and reviews that may help consumers better than others will be retrieved. We compare our model with several machine learning classification algorithms and our experimental results show that our approach effectively classifies online reviews. Also, we provide an evaluation measurement to judge the performance of the helpfulness modeling algorithm and the results show that the helpfulness scores predicted by our approach consistently follow the changing trend of the true helpfulness values.