Interpersonal closeness, or, rapport is an important element of human interaction, particularly in educational contexts, but current educational technologies are often unable to detect or respond to students in ways that draw on research on interpersonal social bonding in learning. In the "Rapport-Aligned Peer Tutor" (or, RAPT) project, we study rapport-building behaviors in peer tutoring in order to design a virtual peer tutor that can build rapport with students.

In this component of the project, we are designing the virtual peer tutoring agent that can tutor students through natural language dialogue and respond in nonverbal and verbal ways to build rapport and better motivate students in learning. We draw on theories and methods from dialogue systems, natural language processing, machine learning, as well as theories of interpersonal human behavior. We are currently in the development phase of building the virtual agent, drawing on our findings from studying human-human peer tutoring behaviors, as well as other work from our lab on building "socially-aware" modules of a dialogue system. We intend to test the first version of this system in summer, 2017.