Iterative group-based and difference ranking method for online rating systems with spamming attacks

Abstract

It is significant to assign reputation scores to users and identify spammers in the bipartite rating networks. In this paper, we propose an Iterative Group-based and Difference Ranking (IGDR) method, which is based on the original Iterative Group-based Ranking (IGR) method. The IGR method considers users grouping behaviors, but it ignores the characteristics of the individual ratings. It is discovered that individual rating characteristics could also contribute to the redistribution of reputation scores of users. The user with a smaller rating deviation will be given a higher reputation score. The proposed method outperforms IGR method ranging from 8% to 163% tested on three real datasets. It also can be applied to deal with big data in a short time.