User-based network embedding for opinion spammer detection.

• This paper jointly learning direct relevance and indirect relevance for collective spammers detection. • The direct relevance is captured by the pairwise behavior features between two users. • The indirect relevance is learned based on a k-step co-rating neighborhood proximity in the network. • Extensive experiments conducted on two real-world datasets verify the effectiveness of the proposed method. Due to the huge commercial interests behind online reviews, a tremendous amount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the influence of spam reviews, spammers often collaboratively post spam reviews within a short period of time, the activities of whom are called collective opinion spam campaign. The goals and members of the spam campaign activities change frequently, and some spammers also imitate normal purchases to conceal the 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 behavior 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. [ABSTRACT FROM AUTHOR]