作者: Shen Hua , Liu XinYue
关键词:
摘要: How to find the features of spammers and link structure is a fundamental issue in social networks. Existing work solves this problem by classification ranking. However, these methods ignore relationship strength on edges, i.e., weight between pair users. Then challenge how effectively estimate given To tackle challenge, paper proposes Poisson regression-based latent variable model jointly modelling users’ similarities interactions’ frequency. Furthermore, Anti-Trust Rank with algorithm proposed fight farming Twitter. Experimental results show that scheme can demote penalize uses effectively. Keywords-Anti-Trustrank; Social Spam; Relationship Strength