Designing engaging intelligent tutoring systems in an age of cognitive computing

Abstract

Advances in human computer interaction (HCI) are enabling increasingly more human-like interactions with computers. In this position paper, we explore the impact of several such advances in HCI on the design of an intelligent tutoring system (ITS), with the hypothesis that such systems may drive deeper engagement and hence improve learning outcomes. Researchers have made claims regarding learning gains resulting from self-explanations, frequent addressing of errors and impasses, rich natural language understanding and dialog, appropriate degree of interactivity, and use of multiple representations. However, many studies on current ITSs that have embodied one or more of the above features are showing little to no discernible impact on learning. This is possibly partly due to the poor user experience. Our tutoring system is aimed at addressing learning challenges for K-12 students, by integrating a suite of differentiating technologies around interactivity, dialog, automated question generation, and learning analytics. In this paper, we first review learning theories and insights gleaned from prior research on ITSs that have inspired our design. We then describe the functional architecture of our tutoring system, followed by a preliminary report on the status of the prototype currently being built.