A team of computer scientists from the University of Miami have created a new algorithm that could help predict when and where the extremist entity—ISIS will carry their next attack.
— University of Miami (@univmiami) June 17, 2016
In an article published in the journal Science, scientists defined their method of using the algorithm to examine through Russian social network Vkontakte and look for pro-ISIS post in multiple languages, and then building a map of recruiting data.
From this data, the team could build a statistical model aimed to decode patterns in the social media activity of Islamic State supporters and will use this data to predict the onset of major violent events.
The scientists have tracked around 108,086 individual followers on ISIS related social media pages, which they referred to as “aggregates”. These groups would originally come together to discuss everything from tips to survive drone strikes to declaration of their extremisms.
‘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,’ the team wrote....