Researchers developed a model aimed at identifying behavioral patterns among online supporters of ISIS and used this information to predict the onset of major violent events. Their data reveal that, even though these pro-ISIS groups comprise members who have likely never met, they display a striking ability to adapt in a way that can extend their online lifetime and increase their size; online groups of civil protestors studied as a control did not exhibit this adaptive ability, by contrast, perhaps because in their online environment, pressures imposed by "cyber police" seeking to shut them down were fewer. Today, the increased connectivity the internet affords terrorist groups is changing their reach, even inspiring individuals with no known history of extremism to operate on their own. However, the behavioral mechanisms that allow such a self-organized cyber system to be sustained are largely unknown. Here, Neil Johnson and colleagues studied detailed records of online support for ISIS, focusing on pro-ISIS "aggregates," or groups of followers of online, pro-ISIS pages created through VKontakte, the largest social networking service in Europe. Through a series of data refinements, they identified 196 pro-ISIS aggregates. The researchers studied when these aggregates shut down in response to online pressure, and then regrouped under different names, among other behaviors. Based on their observations, they developed a systems-level model that offers various predictions; among them, that countermeasures of anti-ISIS agencies can thwart the development of large pro-ISIS aggregates, and further, that if anti-ISIS agencies act insufficiently, pro-ISIS support can grow into one super-aggregate. The authors suggest their model may be used to predict the likelihood of a pro-ISIS activity even when no dates for such events have been circulated.