Online support for adversarial groups such as Islamic State (ISIS) can turn local into global threats and attract new recruits and funding. Johnson et al. analyzed data collected on ISIS-related websites involving 108,086 individual followers between 1 January 1 and 31 August 2015. They developed a statistical model aimed at identifying behavioral patterns among online supporters of ISIS and used this information to predict the onset of major violent events. Sudden escalation in the number of ISIS-supporting ad hoc web groups (“aggregates”) preceded the onset of violence in a way that would not have been detected by looking at social media references to ISIS alone. The model suggests how the development and evolution of such aggregates can be blocked.