Comfort with Uncertainty Predicts Acceptance of Algorithmic Advice

This study explores the influence of individual differences in uncertainty tolerance and source preference on the acceptance of algorithmic advice. By integrating economic lottery choice tasks with decision-making experiments, we examine how comfort with uncertainty shapes behavioral tendencies toward algorithmic or human advisors. Across three tasks varying in objectivity-—crowd counting, remote associates, and caption generation-—we identify an overall algorithmic appreciation effect, where participants favor algorithmic advice, particularly in objective tasks. Importantly, the degree of algorithmic appreciation is contingent upon uncertainty tolerances and source preferences. Further, we identify significant heterogeneity over tasks. Our findings suggest that individual psychological factors, such as a preference for non-social uncertainty sources, predict algorithmic advice acceptance.