Automating the Application of Deception Detection Heuristics to Open Sources

"We propose to construct an intelligent software agent system for identifying misleading information, called Skeptic, atop a foundation of domain-independent heuristics collected and refined during decades of study of successful human detectors ofdeception. The heuristics will provide our Skeptic system with a significant advantage over purely inductive methods by allowing it to exploit the adversarial nature of this problem to effectively anticipate actions of the adversary and inform anevidential reasoning system. Skeptic will be the first deception detection system to employ information extraction to allow the detection of misleading information from Web sites and other open sources. Further, Skeptic's ability to adapt over time (inthe presence of its domain independent heuristics) means it can be deployed early, and mature as the understanding of the problem matures. SHAI presents the opportunity for quick progress due to our existing set of applicable technologies in the areas ofinformation extraction, evidential reasoning, and data/text mining. Phase I research and development of a research prototype will allow us to verify the feasibility of our approach to identifying misleading information and will lay the groundwork for thePhase II implementation of a complete prototype of Skeptic. The proposed technology could be applied to the problem of detecting Medicare or stock fraud, as well as competitive intelligence gathering