A Mythic Belief Regarding Trust in Artificial Intelligence: Uncovering the Role of Responsibility Perception for AI Use in Decision-Making

초록

This study aims to analyze a mechanism of AI responsibility based on attribution theory. It also identifies a new concept, AI locus of control (AI-LOC), reflecting an individual's belief about the degree to which AI determines decision performance. To this end, we built a website with embedded AI systems where participants longitudinally made corporate credit rating decisions. We created a dynamic panel dataset that includes participants' decisions per task and decision performance and attitudes per session. The results revealed that AI-LOC and trust in AI were developed in parallel yet differed over time. AI-LOC positively influenced AI use, but trust in AI did not. We reasoned that individuals would likely exhibit self-serving biases and take an egocentric and disengagement coping strategy regarding their decision-making with AI. This study can contribute to understanding the psychological and behavioral aspects of AI use.

키워드