Personalized Learning Pathways: A Review
Abstract
In today&s;s rapidly evolving educational landscape, personalized learning recommendation systems (PLRS) have become essential for addressing diverse learner needs in an online environment. This review paper provides a comprehensive analysis of recent advancements in adaptive and personalized recommendation techniques for e-learning and Massive Open Online Courses (MOOCs). Drawing the insights from seventeen research studies published between 2012 and 2025, the paper explores various algorithmic techniques such as deep learning, reinforcement learning, knowledge graphs, meta-heuristics, and hybrid models. It highlights how these approaches enhance learner engagement, optimize course sequences, and support flexible learning paths. The study also highlights key research trends, including the integration of retrieval-augmented generation (RAG) and large language models (LLMs), and discusses unresolved challenges such as explainability, scalability, and cross-platform data integration. By bringing together different, frameworks, and evaluation strategies, this paper contributes to a deeper understanding of how intelligent systems are shaping the future of personalized e-learning experiences.
