Content-aware trust propagation toward online review spam detection

Abstract

With the increasing popularity of online review systems, a large volume of user-generated content becomes available to help people make reasonable judgments about the quality of services and products from unknown providers. However, these platforms are frequently abused since fraudulent information can be freely inserted by potentially malicious users without validation. Consequently, online review systems become targets of individual and professional spammers, who insert deceptive reviews by manipulating the rating and/or the content of the reviews. In this work, we propose a review spamming detection scheme based on the deviation between the aspectspecific opinions extracted from individual reviews and the aggregated opinions on the corresponding aspects. In particular, we model the influence on the trustworthiness of the user due to his opinion deviations from the majority in the form of a deviation-based penalty, and integrate this penalty into a three-layer trust propagation framework to iteratively compute the trust scores for users, reviews, and review targets, respectively. The trust scores are effective indicators of spammers, since they reflect the overall deviation of a user from the aggregated aspect-specific opinions across all targets and all aspects. Experiments on the dataset collected from Yelp.com show that the proposed detection scheme based on aspect-specific content-aware trust propagation is able to measure users' trustworthiness based on opinions expressed in reviews.