FUSE: A Fuzzy-Semantic Framework for Personalizing Learning Recommendations

Abstract

The use of instructional Semantic Web rules to deliver personalized learning recommendations has become an emerging trend in intelligent tutoring systems (ITSs) because it enables experts’ domain knowledge to be easily transferred to machine-readable formats. However, many approaches to ITS design using instructional Semantic Web rules have evaluated learners’ performances without considering the uncertainty of the evaluation process or other factors such as learning behavior and speed of response. In this paper, we present an ITS framework named FUSE, which uses a novel recommendation-making mechanism based on a fuzzy-semantic reasoning process and a multiagent system. In this framework, fuzzy reasoning and semantic reasoning are integrated to form a unified reasoning process and provide personalized learning recommendations adaptively and semantically. A field experiment was conducted at a public university. The results indicated that FUSE enabled significant achievements in both enhancing learning performance and increasing learners’ participation in the learning process.