Researchers Develop Data Analytics Methods to Predict Where ISIS Will Attack Next

0
28

In one of the latest displays of the military applications of data analytics, researchers are developing the ability to predict where rebel groups like ISIS will strike next. Based on 2,200 recorded incidents of the group’s activity last year, Arizona State University professor Paulo Shakarian has created an algorithm to do just that.

One of the patterns that was detected was the relationship between air strikes in Syria, and mass arrests by ISIS. When these air strikes were conducted by Syria, ISIS would respond with mass arrests, due to their suspicion of informants within the population. However, coalition air strikes are known by ISIS to be a result of satellite imagery and NSA surveillance, and so they do not bother with the arrests.

Qatar’s Computing Research Institute (CRI) in Doha has developed a Twitter-focused algorithm that has the capability of predicting with 87% accuracy, which users will turn out to be ISIS supporters, before they express an opinion either way.

According to the CRI, one interesting finding was in relation to the Arab Spring.

“The key story that emerges is one of frustration with failed Arab Spring revolutions. Isis supporters largely differ from Isis opposition in that they refer a lot more to Arab Spring uprisings that failed…As for opposition to Isis, it is linked with support for other rebel groups, mostly in Syria, that have been targeted by Isis, support for existing Middle Eastern regimes, and Shia sectarianism.”

As part of its Minerva initiative, the Department of Defense has invested $8 million towards social science research projects similar in nature to those of professor Shakarian. One of these programs also incorporates Twitter, but instead of merely digesting the content of user postings, it attempts to shape insurgent behavior in a delicate propaganda move.

Through recognition of the types of postings that go on to become viral, the system then inserts its own waves of artificial posts in an attempt to shape the dialogue.

Arizona State University’s co-director of the Center on the Future of War, Daniel Rothberg, commented on the new capabilities, “We’ve seen a really substantial shift in how war and conflict are managed in regards to information in recent years…What is kind of radical is the power of analytics. We don’t even know where it’s going because this is so new.”

Stay Connected