Health-Related Spammer Detection on Chinese Social Media

Weibo (Chinese microblog) has become a popular social media platform for users to share health-related information. However, illegitimate users or spammers often generate and spread false or misleading health information so as to advertise and attract more attention. To address this issue, we propose a health-related spammer detection approach on Chinese social media. Our approach is a deep belief network (DBN) based model incorporating a comprehensive feature set, including burstiness-based features, profile-based features, and content-based features, to identify spammers who spread misleading health-related information. Especially, we create a medical and health domain lexicon to better extract content-based features. The experimental results show the approach achieves an F1 score of 86 % in detecting spammer and significantly outperforms the benchmark methods using baseline features.