Predicting terrorist activity

Researchers at the University of Maryland's Institute for Advanced Computer Studies announced this week that they have launched an online portal that will let analysts query rules on the behavior of terrorist organizations and forecast their future behavior.

The SOMA Terror Organization Portal (STOP) is based on a framework of Stochastic Opponent Modeling Agents. A formal, logical-statistical reasoning framework, SOMA uses data about the past behavior of terrorist groups to learn rules about the probability of an organization, community or person taking certain actions in certain situations, institute officials said in a statement. University of Maryland researchers have also used SOMA rules to predict scenarios such as the likelihood of Afghan farmers to grow opium poppies.

V.S. Subrahmanian, the institute's director, a computer science professor and leader of the STOP project, said SOMA can automatically execute rules about behavioral data and 'allow us to infer what a group might do in a real or hypothetical situation.'

SOMA has generated tens of thousands of rules about the likely behavior of 30 groups, such as Hezbollah and Hamas, institute officials said.

STOP contains a table of data about each terrorist group the researchers study, Subrahmanian said. Jonathan Wilkenfeld, a political science professor at the University of Maryland, created the table. Each row denotes a particular year in which the group was active, and each column describes a variable, such as the degree of violence used by a state against the terrorist group. The variables fall into two categories: environmental variables, which describe the environment in which the group operates, and action variables, which denote the intensity of the group's actions.

Subrahmanian and the STOP researchers have 'developed algorithms that automatically examine the data in these tables and automatically identify statistical rules that link the environmental variables and the action variables,' he said. 'Such rules specify the conditions under which the group took a given action.'

'SOMA is a significant joint computer science and social science achievement that will facilitate learning about and forecasting terrorist group behavior based on rigorous mathematical and computational models,' Subrahmanian said. 'But even the best science needs to work hand in hand with social scientists and users. In addition to accurate behavioral models and forecasting algorithms, the SOMA Terror Organization Portal acts as a virtual roundtable that terrorism experts can gather around and form a rich community that transcends artificial boundaries.'

The Defense Department funds the portal, which has users from four defense agencies. It allows for interaction among the users, who can perform queries, run a prediction engine, mark rules as useful or not useful, and post comments.

'Security analysts need more than piles of data,' said Aaron Mannes, a researcher at the institute and author of Profiles in Terror: The Guide to Middle East Terrorist Organizations. 'It takes a network to fight a network. Analysts need to learn from other analysts. This system allows multiple users to arrive at a shared understanding of how a terror group operates and what it might do in the future.'

About the Author

Trudy Walsh is a senior writer for GCN.

inside gcn

  • artificial intelligence (ktsdesign/Shutterstock.com)

    Machine learning with limited data

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group