Early prediction of radicalisation in online extremist communities

Anonymous

Abstract: This study investigates early indicators of radicalisation within online extremist communities. Building upon established counterterrorism research, we identify and analyse three sociolinguistic markers of radicalisation: hostility, longevity and inter-group connectivity. We further develop models to predict the maximum degree of each indicator measured over an individual's lifetime, based on a minimal number of initial interactions. Drawing on data from two diverse extremist communities, our results demonstrate that NLP methods are effective at prioritising at-risk users. It further offers practical insights for intervention and policy development, and highlights an important but under-studied research direction.

Paper Type: long

Research Area: Computational Social Science and Cultural Analytics

Contribution Types: Model analysis & interpretability, Data analysis, Position papers, Theory

Languages Studied: English