Evaluating eye-tracking as a method for deception detection against the polygraph as deployed in practice

Can credibility assessment be based on methods more reliable than those currently used? Traditional polygraph examinations, although widely employed, have well-documented limitations, motivating the search for alternative, noninvasive approaches. In this study, we developed an eye-tracking-based method to detect concealed memory traces by analyzing patterns of eye movements during a Concealed Information Test. Unlike previous research that examined eye movements in isolation, we directly compared the performance of the eye-tracking method with polygraph measurements within the same participants and under identical experimental conditions. Key features extracted from eye movements were used in a machine learning classifier to distinguish between deceptive and truthful responses. The results show that our eye-tracking-based test can effectively discriminate between deceptive and truthful individuals, achieving an accuracy of 94.9%. In comparison, polygraph examinations accurately classified 88.2% of participants under the same conditions, though five recordings had to be excluded because the polygraph expert could not reach a definitive conclusion. Finally, this study also considers the advantages and limitations of the two approaches, as well as ethical concerns related to measuring involuntary responses and using "black box" scoring algorithms.