• University: Carnegie Mellon University
  • Authors: Lujie Chen, Henny Admoni, Artur Dubrawski

Abstract: Challenging math problems without immediate solutions often invite students to ride an “emotional roller-coaster” through episodes of confusion, frustration, surprise and joy. Those problem solving experiences provide rich opportunities to cultivate mathematical perseverance, the mentality to forge ahead in face of ambiguity or difficulty. An ideal teacher closely monitors the problem solving process and provides cognitive, emotional or social supports that are often personalized and optimized. Given the potential high cognitive loads on the teacher who needs to monitor and react in real time, an affect sensitive social robot has the potential to assist by partnering with human teacher in a busy classroom. In this paper, we will describe a multi-modal dataset we collected from multiple sessions of a young child solving math problems coached by his parent tutor. We report initial findings and their implications in the interaction design of a robotic companion that responds dynamically to the child’s fine-grained non-verbal behaviors cues and affect signals in order to foster perseverance. We also describe an ongoing study involving multiple parent-child pairs with additional data elements.