Design and Evaluation of Adaptive E-Learning Platforms Using Learner Behavior Analytics

Abstract

This dissertation focuses on the study of designing and evaluating adaptive e-learning systems with respect to learner behavior analytics. The aim is to improve personalization in learning by dynamically modifying content and learning sequences through real-time data. The approach taken is the creation of a behavior-driven adaptive system based on machine learning algorithms. Evaluation results indicate enhanced learner interaction and academic outcomes using adaptive systems as opposed to conventional systems. The results highlight the opportunities that exist with respect to data-based adaptability in e-learning and the new frontiers it brings forth in personalized education.