Is it truly a 5-star movie?: restoring the movie's truthful rating
Weiyue Huang, Yong Hai Yu · Advances in Social Networks Analysis and Mining · 2016
Authenticity is the key for online review sites. Due to the significant development of review sites, the reviews are now highly important to users, producers and other stakeholders. Driven by interest, some imposters begin to post fake reviews to promote or discredit target products. The fake reviews not only mislead the users but also damage the service provider's credit. Current works mostly aim at classifying whether a specific review is fake or not, using context-based or user-based approaches. However, the aggregated rating of the product is viewer's most concern. Therefore, we propose a novel task to restore the truthful rating and further tackle it by statistical and deep learning techniques. We also assemble and publish a movie-review dataset for this task.