Social spammers disseminate unsolicited information on social media sites that negatively impacts social networking systems. To detect social spammers, traditional methods leverage social network structures to identify the behavioral patterns hidden in their social interactions. They focus on accounts that are affiliated with groups comprising known spammers. However, since different parties are emerging to generate various spammers, they may form different kinds of groups, and some spammers may even detach from the flock. Therefore, it is challenging for existing methods to find the optimal group structure that captures different spammers simultaneously. Employing different approaches for specific spammers is time-consuming, and it also lacks the adaptivity of dealing with emerging spammers. In this work, we aim to propose a group modeling framework that adaptively characterizes social interactions of spammers. In particular, we introduce to integrate content information into the group modeling process. The proposed framework exploits additional content information in selecting groups and individuals that are likely to be involved in spamming activities. In order to alleviate the intensive computational cost, we transform the problem as a sparse learning task that can be solved efficiently. Experimental results on real-world datasets show that the proposed method outperforms the state-of-the-art approaches.
Read full abstract