Deception is a significant and pervasive social phenomenon that touches on many aspects of human life. On average, people tell one to two lies a day, and these lies range from the trivial to the very serious, including deception between friends and family, in the workplace, and in security and intelligence contexts. At the same time, information and communication technologies have pervaded almost all aspects of human communication, from everyday technologies that support interpersonal interactions, such as email and instant messaging, to more sophisticated systems that support organization-level interactions. With this NSF award the research team will draw on communication, psychology, natural language processing and computational linguistics to examine how humans adapt their deceptive practices to new communication and information environments. The primary research questions are: 1) how do computer-mediated environments affect the production and practices of deception? 2) how is our ability to detect deception affected by computer-mediated environments? and 3) can advanced computational and natural language processing techniques be used to analyze and identify deceptive and truthful messages? In addition to behavioral studies of deception production and detection, the project will develop the Deceptive Message Corpus, a large-scale, shared database of several hundred thousand messages coded for deceptiveness that will be made available to the research community to facilitate research on digital deception. By examining deception in mediated environments and building computer-based tools for the detection of deceptive messages, the proposed research will lead to new approaches that will improve our ability to detect digital forms of deception.
