SimilCatch: Enhanced social spammers detection on Twitter using Markov Random Fields
作者：
Highlights：
• highlights
• Social spam evolution is leading to a marked deterioration in the performance of state-of-the-art supervised classifiers.
• The Markov Random Fields formalism allows a hybrid social spam detection model that exploits both users features and their content-based similarity.
• Users content can be exploited to define robust similarity measures.
• Biased and inaccurate prior predictions on users classes can be effectively used in the context of probabilistic graphical models as demonstrated by the significant increase in recall obtained by the proposed approach.
摘要
highlights•Social spam evolution is leading to a marked deterioration in the performance of state-of-the-art supervised classifiers.•The Markov Random Fields formalism allows a hybrid social spam detection model that exploits both users features and their content-based similarity.•Users content can be exploited to define robust similarity measures.•Biased and inaccurate prior predictions on users classes can be effectively used in the context of probabilistic graphical models as demonstrated by the significant increase in recall obtained by the proposed approach.
论文关键词：Social spam detection,Online social networks,Twitter,Supervised learning,Markov random field,Cybersecurity
论文评审过程：Received 27 November 2019, Revised 27 May 2020, Accepted 31 May 2020, Available online 29 June 2020, Version of Record 29 June 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102317
