Face Matching as a Function of Prior Identity Information in Professional Screeners

Abstract

Using a computer-based face matching task we objectively measured face matching performance (reaction time, sensitivity, accuracy) as a function of prior identity source type (Artificial Intelligence (AI), human, none), prior information accuracy (accurate, inaccurate) and task difficulty (high, low) in professional screeners. Participants were required to judge how similar they thought a pair of faces were, to decide whether the faces in each pair were the same person, and then to judge the difficulty of that decision. Professional screeners were more accurate, faster, and, more sensitive when normative task difficulty was low. Professional screeners were also more accurate, faster, and more sensitive when prior identity source information was accurate. There was no main effect of prior identity source type on performance (there was a trend-level effect). Face matching accuracy positively correlated with normative data from non-professional screeners. Professional screeners were more accurate 80.6% of the time, compared to non-professional screeners.