Gender-based multimodal deception detection.

This paper explores gender-based differences in multimodal deception detection. We introduce a new large, gender-balanced dataset, consisting of 104 subjects with 520 different responses covering multiple scenarios, and perform an extensive analysis of different feature sets extracted from the linguistic, physiological, and thermal data streams recorded from the subjects. We describe a multimodal deception detection system, and show how the two genders achieve different detection rates for different individual and combined feature sets, with accuracy figures reaching 80%. Our experiments and results allow us to make interesting observations concerning the differences in the multimodal detection of deception in males and females.