How a computer program can prevent a terrorist attack

After a terrorist attack, the question always arises: could it have been avoided?

The answer may lie at the intersection of data science and social science. A recently funded project by researchers at Colorado State University and Brandeis University aims to create a powerful data-driven tool that can help law enforcement identify individuals who are heading towards violent extremism.

CSU’s Anura Jayasumana, a professor of electrical and computer engineering with a cross-appointment in computer science, and Jytte Klausen of Brandeis were rewarded $731,000 over two years from the National Institute of Justice to develop a “dynamic risk assessment protocol” that can anticipate the imminent risk of violence in individuals. The IT tool would monitor and filter proven risk indicators for radicalization among large databases of people that would be impossible to comb through one by one.

“There is no protocol to identify, in real time, people who are radicalizing,” Jayasumana said. “On top of that, law enforcement doesn’t have the resources to monitor millions of people. … Our goal is to use the identified characteristics as indicators of radicalization and narrow down the risk groups that law enforcement needs to investigate.

Jayasumana is a leader in network science, in addition to being an expert in data science related to pattern and anomaly detection. His expertise ranges from network mapping for the IoT (Internet of Things) to communication between weather radars. He will lead the development of an algorithm that ranks data for the presence of radicalization indicators defined by Klausen’s team.

Western Jihadism Project

The project will be based on Western Jihadism Project which Klausen founded in 2006. The project includes a multimedia data archive that records the growth of jihadism in Western Europe, North America and Australia since the early 1990s. It includes the records of terrorist offenders from 20 countries.

Western jihadism databases include material from personal social networks within jihadist terrorist organizations and their recruitment efforts in Western countries. It contains information on 6,000 or more individuals, 797 plots successfully executed, failed or foiled, and local and international organizations linked to Western jihadist extremists.

For the new partnership with CSU computer scientists, the Brandeis research team will continue its data collection methodology for subjects who commit acts of terror, but will include new data from 2015.

Help law enforcement

Jayasumana said the work could help law enforcement intervene early in some cases, before the person or people commit acts or fully engage in violence.

Data scientists and social scientists cannot work alone in this case, Jayasuamana said. “You really need interaction between these two groups to solve this problem,” he said. “[Social scientists] we can do it on a small scale, and we can do learning and scouting on a large scale, but we have to understand the issues and what needs to be addressed. Bringing these two groups together is important in this regard.

Gordon K. Morehouse