A Real-Time Data Collection System of Visual, Auditory, Read/Write, Kinaesthetic (VARK) Learning Preferences for Personalized Adaptive E-Learning System Model

ABSTRACT

Visual, Auditory, Read/Write, and Kinaesthetic (VARK) offers a widely accepted framework for capturing learner learning preferences. Research has indicated that Traditional VARK data capture system provides a rapid method of classifying learning types and a basic understanding of learner tendencies. However, there are limitations in the areas of accuracy, scalability, and adaptability. Hence, this paper presents the development of a real-time data capture system to classify learners based on the VARK learning style and support dynamic adaptation within an e-learning system. The system continuously collects interaction data through learners’ behaviour analytics, preference inputs, and system usage patterns, which are then, processed using a classification algorithm to infer dominant learning styles in real time. The system was implemented using JavaScript, AJAX and PHP as a client-side and server-side scripting respectively with PostgreSQL as a database. Experimental validation with a diverse group of students demonstrated increased learning satisfaction, content retention, and system usability compared to traditional static e-learning models. The system provides a scalable and intelligent foundation for integrating learning style awareness into modern adaptive learning system.

Keywords: Real-Time, Adaptive E-Learning, VARK, Re-LMS, Learning Preferences.