A Classification of Evaluation Methods for Intelligent Tutoring Systems

Abstract

Evaluation of intelligent tutoring systems (ITS) is an important area of research in current educational practices. There are many evaluation methods available but the literature does not suggest any clear guidelines for an evaluator - normally an educator - which methods to use in particular contexts. This paper proposes a classification of evaluation methods to simplify the selection task. The classification is based on two primary questions relating to the target of evaluation and learning environment in which the evaluation would be pursued. The classification is hoped to help in improving quality of computer based education by providing a practical and to the point way of selecting the appropriate evaluation methods for intelligent tutoring systems.