Concept-based and fuzzy adaptive e-learning (CaFAE)

E-learning systems have been available for several decades and are now ubiquitous in higher education, however, the vast majority of these e-learning systems do not adapt to the student. Adaptive e-learning gives students the appropriate learning materials based on their abilities in the subject area being studied. This thesis presents a novel adaptive e-learning system (CaFAE) that has been designed to show learners their knowledge level for each concept in the subject area using a coloured concept map, and then recommend a bespoke learning path based on a ranked concept list. This work has made several key contributions, including a differential assessment strategy, coloured concept map visualisation, ranked concept list ordering and bespoke learning path. This thesis evaluates the effectiveness of the proposed system by conducting a pilot study at the University of Sussex, followed by a full study with a teaching group as part of the Algorithms and Data Structure course in Prince Sattam bin Abdulaziz University in Saud Arabia. From the experimental outcomes, it can be seen that the proposed system has made an identifiable contribution to the subject understanding for the students who used the interventional (adaptive) system over those who used the non-interventional (non-adaptive) system. These students also show increased engagement and attainment and expressed satisfaction with the system.