Using a Quantitative Model of Participation in a Community of Practice to Direct Automated Mentoring in an Ill-Formed Domain

We describe a system for producing automated professional mentoring using a quantitative model of enculturation. We are developing an automated mentoring technology, AutoMentor, that builds on previous research on automated tutoring systems, specifically on AutoTutor, a computer tutor that helps students learn about science and technology topics by holding a conversation in natural language with the learner. We do this by exploring a specific hypothesis about mentoring in ill-formed domains: namely, that using sociocultural model as the basis of an automated tutoring system can provide a computational model of participation in a community of practice, which will produce effective professional feedback from non-player-characters in a