Estimating global opinions by keeping users from fraud in online review systems

In this work, we focus on online review systems, in which users provide opinions about a set of entities (movies, restaurants, etc.) based on their experiences and in turn can check what others prefer. These systems have been proved to be sensitive to fraud and have shown some shortcomings as a result of capturing opinions through numerical ratings. Thus, supported by recent work on the field, we tackle the problem of fraud in such systems by designing a mechanism based on pairwise comparisons, coupled with an incentive policy attempting to foster the collection of majority opinions over individual experiences. As a result, we propose a new mechanism called iPWRM (incentive-based PWRM), where users are persuaded to reply honestly to pairwise queries based on opinion polls. The idea is: (1) to give a positive reward when all users agree in their reviews; (2) to give a positive reward when a user agrees the majority’s choice; and finally, (3) to give a low incentive—possibly null—when user’s review does not match the majority. Therefore, it is able (1) to overcome the bias introduced into reputation rankings by fraud reviews in ORSs, as well as (2) to mitigate potential biased problems derived from the use of numerical ratings. We exhaustively test the performance of the mechanism by using two different well-known existing datasets Flixster and HetRec2011—real world datasets on movie reviews, aiming to test the performance of the mechanism as well as the effectiveness and efficiency of iPWRM when fraud comes into play.