Deceit detection via online behavioral learning
MetadataShow full item record
We build a framework for an automated deceit detection system which captures deceit by measuring the deviation from normal behavior, at a critical point in the course of an investigative interrogation. Behavioral Psychologists have shown that eyes (via gaze aversion) can be good “reflectors” of the inner emotions, when a person tells a high-stake lie; hence we develop our deceit detection framework around eye movement changes. Deception causes physiological reactions such as high blood pressure, increased heart rate, and an increased respiration rate. Behavioral cues to deceit differ in low- and high-stakes situations, i.e. the nervous behaviors manifested or leaked in people telling lies when the stakes are high are different from when they are low, and high-stake cues are more readily detected. We explore the latent information from the eyes, created while a subject is engaged in a conversation that could potentially result in a high-stake lie being told. Hence we train a Hidden Markov Model with the latent information from the eyes during a normal course of conversation for each subject to represent normal behavior. The remaining conversation is broken into sequences and each sequence is tested against the parameters of the model of normal behavior. At the critical points in the interrogations, the deviations from normalcy are observed and used to deduce verity/deceit. An analysis on 40 subjects gave us an accuracy of 82.5% which strongly suggests that the latent parameters of eye movements successfully capture behavioral changes and could be viable for use in automated deceit detection.