Faces of radicalism: Differentiating between violent and non-violent radicals by their social media profiles
作者：
Highlights：
• Comparing the Facebook behaviors of terrorists and non-violent radicals using a matched case-control design.
• Testing the predictive quality of factors derived from Social Learning Theory.
• Terrorists are more likely to post about a friend's terrorist attack already committed.
• Terrorists engage in more content sharing and non-violent radicals in more text-based posting.
• Automated detection approaches should integrate behavior-level factors to improve accuracy and reduce false-positives.
摘要
•Comparing the Facebook behaviors of terrorists and non-violent radicals using a matched case-control design.•Testing the predictive quality of factors derived from Social Learning Theory.•Terrorists are more likely to post about a friend's terrorist attack already committed.•Terrorists engage in more content sharing and non-violent radicals in more text-based posting.•Automated detection approaches should integrate behavior-level factors to improve accuracy and reduce false-positives.
论文关键词：Terrorism,Case-control,Social-media,Internet,Social-learning theory
论文评审过程：Received 27 June 2020, Revised 22 November 2020, Accepted 28 November 2020, Available online 7 December 2020, Version of Record 10 December 2020.
论文官网地址：https://doi.org/10.1016/j.chb.2020.106646
