Predicting the helpfulness of online customer reviews: The role of title features

Abstract

Nowadays, many people refer to online customer reviews that are available on most shopping websites to make a better purchase decision. An automated review helpfulness prediction model can help the websites to rank reviews based on their level of helpfulness. This study examines the effect of review title features on predicting the helpfulness of online reviews. Moreover, a new method is proposed to categorize action verbs in a review text. Text, reviewer, readability, and title features are the four main categories that are used in this article. We examine our proposed prediction model on two real-life Amazon datasets using machine learning techniques. The results show a promising performance of the model. However, feature importance analysis reveals the low importance of title features in the predictive model. It means that the title characteristics cannot be a powerful determinant of online review helpfulness. The results of this study can be beneficial to both buyers and website owners to have a deep insight into online reviews helpfulness.