LEVERAGING MACHINE LEARNING-DRIVEN RECOMMENDER SYSTEMS FOR ENHANCED STUDENT ENGAGEMENT AND MOTIVATION

DOI: https://doie.org/10.10399/JBSE.2025420040

Mrs. S.Krishnaveni , Dr.K. Dinakaran , Dr.P.Valarmathie

Keywords:

Personalized learning, Massive Open Online Courses (MOOCs), recommender systems, machine learning, E-learning, Student engagement and motivation.

Abstract:

To improve student engagement, retention, and learning results, this study focuses on incorporating customized learning systems into massive open online courses (MOOCs) using RS based on machine learning. There are two issues that massive open online courses (MOOCs) confront, and customized learning systems address them. These challenges are high dropout rates and insufficient individualized assistance. Adapting learning routes based on individual learner profiles may be accomplished by utilizing various recommendation systems, such as collaborative Filtering, reinforcement learning, and hybrid models, as demonstrated by research. As a result, these methods guarantee that students are eager to learn and actively involved in the process, both of which are essential to successful online learning. The study demonstrates how tailored suggestions will respond to changes in the demands of learners by using data such as clickstream and learning behavior. This will result in improved academic achievement and increased levels of pleasure. On the other hand, based on some ethical considerations, particularly about fairness, transparency, and bias in the recommendation algorithm, it is a major concern that these systems exploit learner data. At the same time, there is always a probability of reinforcing bias concerning certain demographics, prior knowledge, or socioeconomic background. Based on the study's findings, a greater focus should be placed on fairness-aware models, in which all students are given equal opportunities to learn, regardless of the situation in which they are learning. This may be accomplished only via the development of bias-reducing algorithms so that learners can take full responsibility for making decisions regarding their educational pursuits. Personalized learning systems hold significant promise to change massive open online courses (MOOCs) by boosting student engagement and retention and improving learning results. This is the other inference that can be drawn from this study. However, for them to be applicable on a big scale, they need to be created with strong ethical considerations to prevent any group of students from being disadvantaged and to guarantee no data privacy breach. Future research has to be planned to improve scalability, fairness, and high ethical standards when establishing individualized models for learning; this will better equip online platforms to be accessible, inclusive, and successful across a global platform.”

PDF