Prediction of student actions using weighted Markov models

Abstract

The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on the degrees of the relations between the predicted user and others. In doing so, a novel way is presented to quantify the similarities between previous students and the current active student. These similarity scores will be used as weights in the weighted Markov model.