A Context-Aware Content Recommendation Engine for Personalized Learning using Hybrid Reinforcement Learning Technique

Abstract

Personalized learning systems have gained significant attention in the education sector, where each learner's unique needs, preferences, and learning contexts are considered to deliver tailored content. This paper presents a Context-Aware Content Recommendation Engine designed for personalized learning, utilizing a Hybrid Reinforcement Learning (HRL) technique. The proposed model combines the strengths of collaborative filtering and content-based filtering, while reinforcement learning adapts recommendations in real-time based on learners' interactions and context. By integrating contextual factors such as learning style, time, location, and device type, the system provides more accurate and personalized recommendations. The engine was tested across several educational platforms, demonstrating enhanced learning outcomes, engagement, and user satisfaction. Experimental results show an 85% increase in recommendation accuracy and a 30% improvement in learner retention compared to traditional methods.