Using Stylistic Topic Models to Detect Deception Through Unusual Linguistic Activity Navy STTR FY2010.A Sol No.: Navy STTR FY2010.A Topic No.: N10A-T029 Topic Title: Using Stylistic Topic Models to Detect Deception Through Unusual Linguistic Activity Proposal No.: N10A-029-0416 Firm: Kitware 28 Corporate Drive Clifton Park, New York 12065-8688 Contact: Jeffrey Baumes Phone: (518) 371-3971 Web Site: http://www.kitware.com Abstract: Analysts are faced with the challenge of sifting through enormous quantities of documents, blog posts, communications, etc. to find deceptive behaviors. We propose novel techniques for efficiently and automatically detecting deception on large data with high accuracy by using methodologies from both stylometry and topic modeling. This combined approach will learn models of authors and will detect unusual behavior based on their unconscious writing style or their topical content, or a combination of both. A comprehensive system will make the algorithmic results accessible through a web service to an intuitive user interface with search, drill-down, and cross-referencing with custom visualizations. This will allow analysts to quickly see the current big picture activity and also to discover particular events or trends of interest. The text analysis expertise of University of California Irvine and the software and visualization expertise of Kitware will provide the correct skill set to build these tools. Phase I will assess the feasibility of the algorithmic and visualization techniques needed for this system. Benefits: This work will result in an open framework for deception detection. By using and contributing to open source systems such as Titan and the Visualization Toolkit (VTK), and using standardized interfaces like web services, this work will build a community interested in developing similar tools for deception detection and scalable text analysis in general. Kitware and UC Irvine will benefit as government entities, corporations, or other institutions recognize our leadership and expertise in this field. This will result in new collaborative efforts and funding to build additional features and custom solutions. Return