Among the most difficult decisions a judge faces is determine credibility. Judges make factual findings. Judges (including this one) are not necessarily better than others at figuring out who is telling the truth. For example, in a controlled study of 110 judges with an average of 11.5 years on the bench, judges did no better than chance in telling who was being truthful and who was not. See Paul Ekman & Maureen O’Sullivan, Who Can Catch a Liar?, 46 Am. Psychologist 913 (1991); Richard Schauffler & Kevin S. Burke, Who Are You Going to Believe?, 49 Court Rev. 124 (2013). Judge Learned Hand once said, “The spirit of liberty is the spirit which is not too sure that it is right.”
So perhaps you might read this cautiously. Kaila Bruer, Sarah Zanette, Xiaopan Ding, Thomas D. Lyon and Kang Lee (University of Regina, University of Toronto, National University of Singapore (NUS), University of Southern California Gould School of Law and Institute of Child Study) have posted Identifying Liars Through Automatic Decoding of Children’s Facial Expressions (Forthcoming in Child Development) on SSRN. Here is the abstract:
This study explored whether children’s (N=158; 4-9 years-old) nonverbal facial expressions can be used to identify when children are being deceptive. Using a computer vision program to automatically decode children’s facial expressions according to the Facial Action Coding System, this study employed machine learning to determine whether facial expressions can be used to discriminate between children who concealed breaking a toy(liars) and those who did not break a toy(nonliars). Results found that, regardless of age or history of maltreatment, children’s facial expressions could accurately (73%) distinguished between liars and nonliars. Two emotions, surprise and fear, were more strongly expressed by liars than nonliars. These findings provide evidence to support the use of automatically coded facial expressions to detect children’s deception.