Enhancing Online Learning: Designing Adaptive and Personalised E-Learning System Design using VARK and Open-Source Applications

Study’s Excerpt/Novelty This study pioneers the development of an adaptive e-learning platform that tailors educational content to individual learning preferences using VARK (Visual, Auditory, Read/Write, Kinesthetic) questions, optimizing material extraction through ontology-based methods. By integrating user-specific models that consider learning style theories and leveraging open-access resources, the system offers a personalized and efficient learning experience. The innovative approach of providing customized learning materials and incorporating real-time feedback mechanisms significantly advances the effectiveness of adaptive e-learning systems in diverse educational contexts. Full Abstract This study investigates the adaptability of e-learning platforms by developing a flexible learning system that evaluates users' learning preferences using VARK (Visual, Auditory, Read/Write, Kinesthetic) questions. The system extracts materials from freely accessible online sources, focusing on usability and diverse criteria. Optimisation with ontology enhances data extraction procedures. Various models are developed to incorporate adaptability and personalisation, notably, the learner's model, which integrates student needs and study domains based on learning style theories. The study significantly enhances adaptive e-learning systems by delivering personalised learning materials efficiently sourced from open-access apps and search engines. Evaluation and feedback mechanisms at the start of each session tailor the learning experience to individual styles, thereby improving learning effectiveness in diverse educational settings.