Effect of Robot Tutor's Feedback Valence and Attributional Style on Learners

This study investigated the effect of a robot tutor's feedback valence (positive feedback and negative feedback) and attributional style (internal-attribution and external-attribution) on learners. A Nao robot was designed to be a dance tutor that taught participants dance movements and gave performance feedback. Thirty-six graduate and undergraduate students participated in the experiments and were divided into two groups: an internal-attribution group and an external-attribution group. Participants in each group received both positive and negative feedback. The results indicated that the participants were more likely to accept positive feedback than negative feedback. In addition, they perceived greater influence by positive feedback than negative feedback. Moreover, participants did not the demonstrate self-serving attributional bias. They attributed more blame to themselves than to the robot for negative performance, whereas no difference was observed in the attribution of credit between the robot and the participants. Furthermore, the internal-attribution robot tutor was more likely to be regarded as a training coach instead of a training tool than the external-attribution robot tutor. Finally, participants reported a higher relationship closeness with the internal-attribution robot tutor than the external-attribution robot tutor.