Online social networks have become popular platforms for spammers to spread malicious content and links. Existing state-of-the-art optimization methods mainly use one kind of user-generated information (i.e., single view) to learn a classification model for identifying spammers. Due to the diversity and variability of spammers' strategies, spammers' behavior may not be completely characterized only by single view's information. To tackle this challenge, we first statistically analyze the importance of considering multiple view information for spammer detection task on a large real-world Twitter dataset. Accordingly, we propose a generalized social spammer detection framework by jointly integrating multiple view information and a novel social regularization term into a classification model. To keep the completeness of the original dataset and detect more spammers by the proposed method, we introduce a simple strategy to fill the missing data for each view. Experimental results on a real-world Twitter dataset show that the proposed method outperforms the existing methods significantly.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence