Evidence Aggregation Based Spam Detection in e-Commerce Social Network

Ranking spam in the Social Media and Social Network market refers to fake or deceptive activities which have a purpose of striking up the products and the services for different interests in the popularity list. Indeed, it becomes more and more repeated for Social Networks to use sheltered means, such as inflating their products sales or posting services of the product ratings, to commit ranking spam. While the importance of preventing ranking spamming has been recognized, we provide a holistic inspection of ranking spam and propose a spamming detection system for social network. We propose to exactly locate the ranking spam by mining the active periods, namely leading sessions, of social network. Such sessions can be influenced for detecting the actual rating instead of spammed rating of product rankings. by modeling social networks ranking, rating and review behaviors in the course of statistical proposition tests.