Automatic Detection of Cyber-Recruitment by Violent Extremists

This article presents methods for identifying the recruitment activities of violent groups within extremist social media websites. It focuses on how online communities enable violent extremists to increase recruitment by allowing them to build personal relationships with a worldwide audience capable of accessing uncensored content. Specifically, the methods and techniques described within this paper apply known techniques within supervised learning and natural language processing to the untested task of automatically identifying forum posts intended to recruit new violent extremist members. Evaluation with receiver operating characteristic (ROC) curves shows that the researchers’ SVM classifier achieves an 89% area under the curve (AUC), a significant improvement over the 63% AUC performance achieved by their simplest naive Bayes model (Tukey’s test at p=0.05).

As one of the first successful tests of an automatic detection software on terrorist recruitment, this source is of great importance to the Natural Language Processing field. Moreover, since increasingly frequent use of the internet as a major means of communication has led to the formation of cyber-communities, which have become increasingly appealing to terrorist groups due to the unregulated nature of Internet communication, the research that this study brings to the fore will likely be very attractive to researchers focusing on web terrorism.