STAB: Story Abduction for Proactive Intelligence

We are developing computational techniques for recognizing story plots connecting (apparently isolated) events. The goal is to recognize story plots early enough to make useful predictions about future events. Work is currently done on the VAST dataset synthesized by PNNL, which contains news stories about numerous events, including some 120 events pertaining to illegal or unethical activities in a hypothetical community.
 
 Generic patterns of illegal and unethical activities are represented as hierarchically-organized task-method structures in a Task-Method-Knowledge Language (TMKL). Specific input events and specific output predictions are represented as tasks and methods in TMKL. Input events are viewed as instances of the generic structures in the stored patterns (see figure). A pattern is invoked when an input event matches a generic structure in the stored pattern. The confidence in the invoked pattern is raised as additional events match more of its parts, and lowered if an event violates the generated expectations.