Trust dynamics and user attitudes on recommendation errors: preliminary results
This addresses trust issues in AI recommender systems for users, but it is incremental as it builds on existing models with preliminary simulation results.
The paper tackled the problem of how good and bad recommendations affect user trust in an idealized recommender system with limited capacity, finding through simulations that users eventually accept recommendations under certain conditions and that user attitudes significantly impact trust dynamics.
Artificial Intelligence based systems may be used as digital nudging techniques that can steer or coerce users to make decisions not always aligned with their true interests. When such systems properly address the issues of Fairness, Accountability, Transparency, and Ethics, then the trust of the user in the system would just depend on the system's output. The aim of this paper is to propose a model for exploring how good and bad recommendations affect the overall trust in an idealized recommender system that issues recommendations over a resource with limited capacity. The impact of different users attitudes on trust dynamics is also considered. Using simulations, we ran a large set of experiments that allowed to observe that: 1) under certain circumstances, all the users ended accepting the recommendations; and 2) the user attitude (controlled by a single parameter balancing the gain/loss of trust after a good/bad recommendation) has a great impact in the trust dynamics.