Missing Pieces: How Framing Uncertainty Impacts Longitudinal Trust in AI Decision Aids – A Gig Driver Case Study

Decision aids based on artificial intelligence (AI) are becoming increasingly common. When such systems are deployed in environments with inherent uncertainty, following AI-recommended decisions may lead to a wide range of outcomes. In this work, we investigate how the framing of uncertainty in outcomes impacts users' longitudinal trust in AI decision aids, which is crucial to ensuring that these systems achieve their intended purposes. More specifically, we use gig driving as a representative domain to address the question: how does exposing uncertainty at different levels of granularity affect the evolution of users' trust and their willingness to rely on recommended decisions? We report on a longitudinal mixed-methods study (n = 51) where we measured the trust of gig drivers as they interacted with an AI-based schedule recommendation tool. Statistically significant quantitative results indicate that participants' trust in and willingness to rely on the tool for planning depended on the perceived accuracy of the tool's estimates; that providing ranged estimates improved trust; and that increasing prediction granularity and using hedging language improved willingness to rely on the tool even when trust was low. Additionally, we report on interviews with participants which revealed a diversity of experiences with the tool, suggesting that AI systems must build trust by going beyond general designs to calibrate the expectations of individual users.