Ontology based E-learning framework: A personalized, adaptive and context aware model

• Published in: Multimedia tools and applications Vol. 78; no. 24; pp. 34745 - 34771
• Main Authors: Sarwar, Sohail, Qayyum, Zia Ul, García-Castro, Raúl, Safyan, Muhammad, Munir, Rana Faisal
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2019; Springer Nature B.V
• Subjects: Classification; Computer Communication Networks; Computer Science; Customization; Data Structures and Information Theory; Distance learning; Evaluation; Machine learning; Mathematical models; Multimedia Information Systems; Neural networks; Online instruction; Ontology; Productivity; Special Purpose and Application-Based Systems; System effectiveness; Ontologies; Adaptivity; Personalization; Content Recommender; E-Learning
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-019-08125-8

Enhancing the degree of learner productivity, one of the major challenges in E-Learning systems, may be catered through effective personalization, adaptivity and context awareness while recommending the learning contents to the learners. In this paper, an E-Learning framework has been proposed that profiles the learners, categorizes the learners based on profiles, makes personalized content recommendations and performs assessment based content adaptation. A mathematical model has been proposed for learner categorization using machine learning techniques (a hybrid of case based reasoning and neural networks). The learning contents have been annotated through CourseOntology in which three academic courses (each for language of C++, C# and JAVA) have been modeled for the learners. A dynamic rule based recommender has been presented targeting a ‘relative grading system’ for maximizing the learner’s productivity. Performance of proposed framework has been measured in terms of accurate learner categorization, personalized recommendation of the learning contents, completeness and correctness of ontological model and overall performance improvement of learners in academic sessions of 2015, 2016 and 2017. The comparative analysis of proposed framework exhibits visibly improved results compared to prevalent approaches. These improvements are signified to the comprehensive attribute selection in learner profiling, dynamic techniques for learner categorization and effective content recommendation while ensuring personalization and adaptivity.