Charles River AnalyticsÂ said Thursday it will apply a linguistic feature-based machine learning approach and a grammar toolkit in efforts to develop bias classification technologyÂ under the Defense Advanced Research Projects Agency's Causal Exploration program.
DARPA seeksÂ a causal modeling platform forÂ military planners to determineÂ what factors drive aÂ conflict situation.
Robert Hyland, principal scientist at Charles River Analytics, said the partnership with Raytheon BBN seeks to establish theÂ foundation for a system to detectÂ propaganda and information activity.
â€œThe U.S. military needs better methods to deal with adversary scale and complexity; these adversarial techniques interweave into open and free press and information spaces,â€ Hyland added.
Charles River Analytics used natural language processing techniques to trace, analyze and address information signals from technical documentsÂ and news briefings under the THREAT and ALARMM projects.