A Bayesian student model for ERST - an External Representation Tutor

This paper describes the process by which we are constructing an intelligent tutoring system (ERST) designed to improve learners' external representation (ER) selection accuracy on a range of database query tasks. This paper describes how ERST's student model is being constructed - it is a Bayesian network with values seeded from data derived from two experimental studies. The studies examined the effects of students' background knowledge-of-external representations (KER) upon performance and their preferences for particular information display forms across a range of database query types.