Evaluating the Feasibility of Learning Student Models from Data

Recent work on intelligent tutoring systems has used Bayesian networks to model students ’ acquisition of skills. In many cases, researchers have hand-coded the parameters of the networks, arguing that the conditional probabilities of models containing hidden variables are too difficult to learn from data. We present a machine learning approach that uses Expectation-Maximization to learn the parameters of a dy-namic Bayesian network with hidden variables. We test our methodology on data that was simulated using a state-based model of skill acquisition. Results indicate that it is possi-ble to learn the parameters of hidden variables given enough sequential data of training sessions on similar problems