Evaluating a Bayesian Student Model of Decimal Misconceptions.

Abstract

Among other applications of educational data mining, evaluation of student models is essential for an adaptive educational system. This paper describes the evaluation of a Bayesian model of student misconceptions in the domain of decimals. The Bayesian model supports a remote adaptation service for an Intelligent Tutoring System within a project focused on adaptively presenting erroneous examples to students. We have evaluated the accuracy of the student model by comparing its predictions to the outcomes of students’ logged interactions from a study with 255 school children. Students’ logs were used for retrospective training of the Bayesian network parameters. The accuracy of the student model was evaluated from three different perspectives: its ability to predict the outcome of an individual student’s answer, the correctness of the answer, and the presence of a particular misconception. The results show that the model’s predictions reach a high level of precision, especially in predicting the presence of student misconceptions.