Eye Movements as Indicators of Deception: A Machine Learning Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912361445588992 |
|---|---|
| author | Foucher, Valentin de Leon-Martinez, Santiago Moro, Robert |
| author_facet | Foucher, Valentin de Leon-Martinez, Santiago Moro, Robert |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02649 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Eye Movements as Indicators of Deception: A Machine Learning Approach Foucher, Valentin de Leon-Martinez, Santiago Moro, Robert Human-Computer Interaction Artificial Intelligence Machine Learning 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. |
| title | Eye Movements as Indicators of Deception: A Machine Learning Approach |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.02649 |