Student Profiling and Resource Tagging Using Machine Learning for Adaptive Learning Systems

Abstract

Personalized learning has become a central focus in modern education, aiming to adapt content and support to individual learner needs. This study investigates how students can be grouped according to their learning characteristics, and how educational materials can be classified based on their instructional value

The objective is to enhance recommendation systems in education by providing learners with more relevant resources, while taking into account both their learning styles and the nature of the content.

 To support this goal, real-world data was collected from a private secondary school, involving students from different grade levels. The study compares various classification strategies to determine which are most effective in supporting adaptive learning environments.

The findings contribute to ongoing efforts to make learning more targeted, efficient, and student-centered by leveraging data-driven approaches to profile learners and educational content.