Eye Movements as Indicators of Deception: A Machine Learning Approach

Eye Movements, Gaze, Pupil, Deception Detection, Concealed Information Test, Machine Learning,
Feature Importance

Gaze can enhance the robustness of lie detectors, but remains understudied. This study evaluated the effectiveness of AI models (using fixations, saccades, blinks, and pupil size) for detecting deception in hidden information tests in two datasets. The first, collected with the Eyelink 1000, contains gaze data from a computer experiment in which 87 participants revealed, concealed, or faked the value of a previously selected card. The second, collected with the Pupil Neon, included 37 participants performing a similar task but facing an experimenter. The AI models (XGBoost) achieved up to 74% accuracy in a binary classification task (Reveal vs. Hide) and 49% in a more challenging three-classification task (Reveal vs. Hide vs. Fake). Feature analysis identified saccade count, duration, and amplitude, along with maximum pupil size, as the most important for predicting deception. These results demonstrate the feasibility of using vision and artificial intelligence to improve lie detectors and will encourage future research that could improve this.