THE ROLE OF PROBABILITY-BASED INFERENCE IN AN INTELLIGENT TUTORING SYSTEM

Probability-based inference in complex networks of interdependent vari ables is an active topic in statistical research, spurred by such dive rse applications as forecasting, pedigree analysis, troubleshooting, a nd medical diagnosis. This paper concerns the role of Bayesian inferen ce networks for updating student models in intelligent tutoring system s (ITSs). Basic concepts of the approach are briefly reviewed, but the emphasis is on the considerations that arise when one attempts to ope rationalize the abstract framework of probability-based reasoning in a practical ITS context. The discussion revolves around HYDRIVE, an ITS for learning to troubleshoot an aircraft hydraulics system. HYDRIVE s upports generalized claims about aspects of student proficiency throug h probability-based combination of rule-based evaluations of specific actions. The paper highlights the interplay among inferential issues, the psychology of learning in the domain, and the instructional approa ch upon which the ITS is based.