Evaluation of Etiquette Strategies to Adapt Feedback In Affect-Aware Tutoring

The purpose of this research is to investigate how to mitigate user frustration and improve task performance in the context of human-computer interaction (HCI). Even though user frustration plays a role in many aspects of HCI and studies have looked into the consequences of frustration in various fields, the ways to mitigate frustration are less deeply examined. Once the system has the ability to understand and include user emotions as factors in HCI, the interaction between the user and the computer system could be adapted if the computers are able to modify its behavior with users in appropriate ways to further joint performance. Specifically, a preliminary study was conducted to explore the task performance, motivation, and confidence implications of changing the interaction between the human and the computer via different etiquette strategies. Participants solved a total of twenty mathematics problems under different frustration condition with feedback given in different styles of etiquette. Changing etiquette strategies in tutoring led to changes in performance, motivation, and confidence. The most effective etiquette strategies changed when users were frustrated. This work provides the foundation for the design of adaptive intelligent tutoring system based on etiquette strategies.