用眼动数据和机器学习识别说谎，准确率最高达74%
Eye Movements as Indicators of Deception: A Machine Learning Approach
- 结合眼动特征训练XGBoost模型，区分真实、隐瞒和伪装
- 在两项实验中，二分类准确率达74%，三分类达49%
- 关键特征包括眼跳次数、时长、幅度和瞳孔最大尺寸
眼动可能提升测谎设备的鲁棒性，但研究仍不足。本研究评估了基于注视、眼跳、眨眼和瞳孔大小的AI模型，在两个数据集上对隐蔽信息测试中说谎行为的检测效果。首个数据集使用Eyelink 1000采集，包含87名参与者在电脑实验中揭示、隐瞒或伪装一张事先选定卡片数值的轨迹；第二个数据集使用Pupil Neon采集，36名参与者面对实验员执行相似任务。XGBoost模型在二分类任务（揭示 vs. 隐瞒）中最高达到74%准确率，在更具挑战性的三分类任务（揭示 vs. 隐瞒 vs. 伪装）中达到49%。特征分析显示，眼跳数量、持续时间、幅度及最大瞳孔尺寸是预测说谎的关键因素。结果表明，结合眼动与人工智能可有效增强测谎能力，为后续研究提供方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。