Personalized E-Learning System by Using Item Response Theory

Abstract

Personalized service is an important issue on the Web, especially on Web-based learning. In general, most personalized systems consider learners’ preferences, interests, and browsing behaviors to provide personalized services. However, learners’ abilities are usually neglected as an important factor to implement personalized mechanism. Besides, too many hyperlink structures on Web-based learning systems bring a large number of information burdens to learners. Hence, in Web-based learning, disorientation (losing in hyperspace), cognitive overload, lack of adaptive mechanism, the information overload problem, and the adaptation of course materials’ difficulties are main research issues. In this study, a personalized e-learning system based on Item Response Theory (PEL-IRT) which considers both the difficulties of course materials and learners’ abilities is proposed to provide personalized learning. The item characteristic function with single difficult parameter is used to model a course material. Moreover, the maximum likelihood estimation (MLE) is applied to estimate the learners’ abilities based on learners’ explicit feedback. We also propose a collaborative voting approach to adjust the difficulties of the course materials in order to appropriately determine the difficulties of the course materials. Experimental results show that Item Response Theory applied to Web learning can achieve personalized learning and assist learners to learn more effectively and efficiently.