Semi-Supervised Social Spammer Detection

Social networks, like Twitter and Sina Weibo, are novel web services for online communication and information dissemination. People in social networks can share interested topics via sending short messages which contains plain text and URLs. This kind of web services which combine both micro-blogging and social relationship has attracted more and more users. At the same time, social network have become the main target web platform for spammers to spread unwanted information.Spammers create large number of compromised or fake accounts to disseminate harmful information in social networks like Twitter. Identifying social spammers has become a challenging problem. Most of existing algorithms for social spammer detection are based on supervised learning, which needs a large amount of labeled data for training. However, labeling sufficient training set costs too much resources, which makes supervised learning impractical for social spammer detection.In this paper, we propose a semi-supervised framework for social spammer detection(SSSD), which combines the supervised classification model with a ranking scheme on the social graph. First, we train an original classifier with a small number of labeled data. Second, we propose a ranking model to propagate trust and distrust on the social graph. Third, we select confident users that are judged by the classifier and ranking scores as new training data and retrain the classifier. We repeat the all steps above until the classifier cannot be refined any more. Experimental results show that our framework can effectively detect social spammers in the condition of lacking sufficient labeled data.