Towards a Context-Aware Adaptive e-Learning Architecture

E-learning is increasingly becoming the preferred delivery mode in learning institutions as it allows any time anywhere learning. However, content delivery, access, distribution and personalization are still a challenge. Moreover, ambiguity of students during decision making for their preferred courses has not been addressed. This paper proposes an adaptive e-learning model, an architecture for the adaptation of learning course materials considering students' profiles and their context information. Integration of fuzziness with processes of customization and selection of adequate material for the user creates a chance to build truly personalized and adaptive systems. This adaptive model is helpful in recommending course materials to students or adapting them depending on their context. It complements instructors' efforts in the delivery of learning materials relevant to their personal profiles. An AeLModel architecture is presented taking a full advantage of ontology, tagging, and users' feedback represented with linguistic descriptors and quantifiers. A prototype was developed and tested using 20 students in a class to assess this model's usability in addition to its adherence to content adaptation, resulting in a 77% of acceptance. It is recommended for this to be used in improving learning processes.