User-based Network Embedding for Collective Opinion Spammer Detection
This addresses the challenge of spam detection in e-commerce and review platforms, where spammers collaborate to manipulate product reputations, though it is incremental as it builds on existing network embedding techniques.
The paper tackles the problem of detecting collective opinion spammers in online reviews by proposing an unsupervised network embedding approach that leverages user relations, achieving average improvements of 14.09% to 16.25% in AP and 12.04% to 12.78% in AUC over state-of-the-art methods on datasets like AmazonCn and YelpHotel.
Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the influence of spam reviews, spammers often collaboratively post spam reviewers within a short period of time, the activities of whom are called collective opinion spam campaign. As the goals and members of the spam campaign activities change frequently, and some spammers also imitate normal purchases to conceal identity, which makes the spammer detection challenging. In this paper, we propose an unsupervised network embedding-based approach to jointly exploiting different types of relations, e.g., direct common behaviour relation and indirect co-reviewed relation to effectively represent the relevances of users for detecting the collective opinion spammers. The average improvements of our method over the state-of-the-art solutions on dataset AmazonCn and YelpHotel are [14.09%,12.04%] and [16.25%,12.78%] in terms of AP and AUC, respectively.