Pingjing Yang

This study applies methods of explainable artificial intelligence (XAI) to evaluate the effects of algorithm explanations on human perceptions of algorithms. With control experiments, this study will uncover the connections between explanations and human acceptance, satisfaction, and trust in AI algorithms. Yang’s work aims to deepen our knowledge of human perceptions of algorithms and corresponding explanations, making artificial intelligence more accessible to a larger audience, and resulting in increased adaptation of the technology and its benefits.