How does one predict where a terrorist could strike next? Of course gaining the information beforehand like undercover or spy work is one way, or like we reported last month, spikes on certain YouTube videos could also indicate an imminent attack, but now a group of physicists are hoping to use algorithms to better predict where terrorists could attack.A team led by Neil Johnson from the University of Miami recently published a study based on their findings, which involved sifting through posts that are pro-Islamic State on Vkontakte, a Russian-based social media platform that is more or less Europe’s answer to Facebook. They filtered posts that mentioned activities like beheadings and blood baths in multiple languages.
The end result is that based on their findings, they managed to develop an algorithm that could potentially help predict attacks that are about to happen. Now while it might be obvious to try and focus on the larger pro-ISIS groups, the study actually decided to focus on the smaller groups because according to The New York Times (via Engadget), “they reflect groundswells of new activity and, if followed, can potentially point to where that activity is going.”
That being said, it remains to be seen if this algorithm is strictly theoretical or if there could be practical application. According to J. M. Berger, a fellow in George Washington University’s Program on Extremism, “This is an interesting approach, this is a potentially valuable approach, and more research should be done on the approach, but to jump ahead to the utility of it, I think, takes more work.”
Filed in . Read more about AI (Artificial Intelligence) and Science.