Applying recommender systems and adaptive hypermedia for e-learning personalization

Abstract

Learners learn differently because they are different - and they grow more distinctive as they mature. Personalized learning occurs when e-learning systems make deliberate efforts to design educational experiences that fit the needs, goals, talents, and interests of their learners. Researchers had recently begun to investigate various techniques to help teachers improve e-learning systems. In this paper we present our design and implementation of an adaptive and intelligent webbased programming tutoring system - Protus, which applies recommendation and adaptive hypermedia techniques. This system aims at automatically guiding the learner's activities and recommend relevant links and actions to him/her during the learning process. Experiments on real data sets show the suitability of using both recommendation and hypermedia techniques in order to suggest online learning activities to learners based on their preferences, knowledge and the opinions of the users with similar characteristics.