Gaze-Speech Coordination Influences the Persuasiveness of Human-Robot Dialog in the Wild

摘要

In this study, we argue that the extent to which a robot is persuasive depends on the way a persuasive message is embedded in the robot's other behaviors. In the current study, in which a robot serves water at a large public event, we find that the same robot utterance, namely skal (cheers) when serving water, is received very differently depending on whether the robot is oriented to the user or not. In particular, if the robot gazes at the user while saying skal, almost all users drink immediately, whereas only 44.5% of the people drink if the robot is looking elsewhere. Similarly, the effectiveness of a water-related joke as a persuasive means depends on previously established mutual gaze. Thus, gaze and speech behavior have to be coordinated to improve the robot's persuasiveness in the wild.