Detecting Spammers on Twitter Based on Content and Social Interaction

Twitter has become a target platform on which spammers spread large amounts of harmful information. These malicious spamming activities have seriously threatened normal users' personal privacy and information security. An effective method for detecting spammers is to learn a classifier based on user features and social network information. However, social spammers often change their spamming strategies for evading the detection system. To tackle this challenge, latent user features factorized by text matrix are adopted to capture the consistency of users' behavior. Also, a new social regularization based on users' interaction is introduced to distinguish different types of users. Finally, Supervised Spammer Detection method with Social Interaction is proposed, which jointly learn a classifier by using combine text content, social network information and labeled data. Experimental results on a real-world Twitter dataset confirm the effectiveness of the proposed method.