Automatic Detection of Learning Styles on Learning Management Systems using Data Mining Technique

Objectives: Automatic detection of E-learners’ learning styles is an important requirement for personalized e-learning. The present study proposes the detection of students’ learning styles automatically on Learning Management System (LMS). Methods/Analysis: The present study proposes different technique of automatic detection of learning styles on LMS using Data Mining technique Bayesian Network (BN). A large survey data is used to map the class room learning styles to E-learning environment which provide significance to incorporated LS model on E-learning systems. Standard questionnaire called Kolb’s Learning Style Inventory (KLSI) is used to identify the students’ learning styles in a class room environment but the proposed technique can automatically detect the learning styles on LMS. Findings: The BN resulted probability values were used as threshold values to detect the learning styles of students in an experiment in which the students of a public university of Pakistan were participated. The participants’ learning styles were found using the manual method and the proposed method. The experiment provided promising results. Novelty/Improvement: Personalized E-learning systems are used to maximize the learning in terms of providing the learning objects as per the students’ requirements. The BN technique is used to replace the KLSI to detect the learners’ learning styles on LMS automatically.