Effects of personality traits on user trust in human–machine collaborations

Data analytics-driven solutions are widely used in various intelligent systems, where humans and machines make decisions collaboratively based on predictions. Human factors such as personality and trust have significant effects on such human–machine collaborations. This paper investigates effects of personality traits on user trust in human–machine collaborations under uncertainty and cognitive load conditions. A user study of 42 subjects in a repeated factorial design experiment found that uncertainty presentation led to increased trust but only under low cognitive load conditions when users had sufficient cognitive resources to process the information. Presentation of uncertainty under high load conditions led to a decrease in trust. When further drilling down into personality trait groups of users, overall, users with low Openness showed the highest trust. Furthermore, under the low cognitive load condition, it was found that the trust was enhanced under ambiguity uncertainty with low Agreeableness, low Neuroticism, high Extraversion, high Conscientiousness, and high Openness. Under the high cognitive load condition, high Neuroticism and low Extraversion benefitted the trust without the uncertainty presentation. The results demonstrated that different personality traits affected trust differently under uncertainty and cognitive load conditions. A framework of user trust feedback loop was set up to incorporate the study results into human–machine collaborations for the meaningful participatory design.