Together with my co-authors Ronald Poppe, Paul Taylor, Ross Anderson, and Remco Veltkamp, I conducted a bottom-up analysis of which behaviors are most indicative of deceit. For this purpose, we ran an experiment in which 90 pairs of participants, each pair consisting of an interviewee and an interviewer, talked about a stolen wallet and a game ‘never end’. We varied dimensions such as window length and feature type to determine what was the most accurate way of identifying deceit. Our classification performance reached a 60% accuracy, which was significantly better than both chance (50%) and human performance (52.8%).
Poppe, R. W., Van Der Zee, S., Taylor, P. J., & Veltkamp, R. (2015). Mining bodily cues to deception. Conference Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium, 48th HICSS (5-8 January, 2015).
A significant body of literature has reported research on the potential correlates of deception and bodily behavior. The vast majority of these studies consider discrete bodily movements such as specific hand or head gestures. While differences in the number of such movements could be an indication of a subject’s veracity, they account for only a small proportion of all performed behavior. Such studies also fail to consider quantitative aspects of body movement: the precise movement direction, magnitude and timing are not taken into account. In this paper, we present and discuss the results of a systematic, bottom-up study of bodily correlates of deception. We conducted a user experiment where subjects either were deceptive or spoke the truth. Their body movement was measured using motion capture suits yielding a large number of global and local movement descriptors. We present statistical results on the mining of bodily cues. Our analyses support the feasibility, and report the performance, of automatic deception classification from body movement.