The Impact of personalized educational recommender systems on learning efficiency in higher education

Abstract

In today's academic landscape, university students face challenges in identifying relevant and high-quality educational resources due to the overwhelming availability of digital content. The process of locating specific materials or answers to academic queries often requires navigating vast and irrelevant information, leading to inefficiencies in learning. This research addresses these challenges by developing a personalized educational recommender system that integrates machine learning techniques with the advanced capabilities of Large Language Models (LLMs). Unlike traditional recommender systems that focus solely on suggesting materials, the proposed solution is designed to deliver personalized recommendations and provide precise answers to students’ specific inquiries. This approach aims to align recommended resources with students’ academic modules and research objectives, fostering a more tailored and effective learning experience. The primary objectives of this study include designing the recommender system to support personalized learning and evaluating its impact on students’ learning outcomes, engagement, and motivation. By simplifying access to relevant materials and addressing individual learning needs, this system seeks to enhance the efficiency and quality of the academic experience. Ultimately, the research contributes to advancing learning technologies, making it easier for students to achieve their academic goals while addressing the growing challenges of information overload.