IntroductionArtificial Intelligence (AI) has the capability to create visual images with minimal human input, a technology that is being applied to many areas of daily life. However, the products of AI are consistently judged to be worse than human-created art, even when comparable in quality. The purpose of this study is to determine whether explicit cognitive bias against AI is related to implicit perceptual mechanisms active while viewing art.MethodsParticipants’ eye movements were recorded while viewing religious art, a notably human domain meant to maximize potential bias against AI. Participants (n = 92) viewed 24 pieces of Biblically-inspired religious art, created by the AI tool DALL-E 2. Participants in the control group were told prior to viewing that the pieces were created by art students, while participants in the experimental group were told the pieces were created by AI. Participants were surveyed after viewing to ascertain their opinions on the quality and artistic merit of the pieces.ResultsParticipants’ gaze patterns (fixation counts, fixation durations, fixation dispersion, saccade amplitude, blink rate, saccade peak velocity, and pupil size) did not differ based on who they believed created the pieces, but their subjective opinions of the pieces were significantly more positive when they believed pieces were created by humans as opposed to AI.DiscussionThis study did not obtain any evidence that a person’s explicit “valuation” of artworks modulates the pace or spatial extent of visual exploration nor the cognitive effort expended to develop an understanding of them.
