Eye Movements as Indicators of Deception: A Machine Learning Approach
This work addresses the problem of improving lie detectors for applications like security or psychology, but it is incremental as it builds on existing methods with new data.
This study tackled the problem of detecting deception by using AI models to analyze gaze data (fixations, saccades, blinks, and pupil size) in Concealed Information Tests, achieving up to 74% accuracy in binary classification and 49% in three-class classification.
Gaze may enhance the robustness of lie detectors but remains under-studied. This study evaluated the efficacy of AI models (using fixations, saccades, blinks, and pupil size) for detecting deception in Concealed Information Tests across two datasets. The first, collected with Eyelink 1000, contains gaze data from a computerized experiment where 87 participants revealed, concealed, or faked the value of a previously selected card. The second, collected with Pupil Neon, involved 36 participants performing a similar task but facing an experimenter. XGBoost achieved accuracies up to 74% in a binary classification task (Revealing vs. Concealing) and 49% in a more challenging three-classification task (Revealing vs. Concealing vs. Faking). Feature analysis identified saccade number, duration, amplitude, and maximum pupil size as the most important for deception prediction. These results demonstrate the feasibility of using gaze and AI to enhance lie detectors and encourage future research that may improve on this.