With the rapid evolution of e-learning platforms, the need for personalized educational resources becomes significant to enhance student engagement and improve learning outcomes. This paper presents a novel approach for generating personalized learning recommendations through integrating association rule mining and semantic web technologies. Through association rule mining, our approach identifies significant patterns and associations from student behavior within educational datasets. These patterns are used in providing recommendations of learning resources, facilitating an adaptive learning environment that aligns with student needs and preferences in a personalized manner. Meanwhile, semantic web technologies structure the educational data providing them with semantics, allowing the system to better understand the relationships between different educational elements effectively. This integration allows obtaining highly relevant educational recommendations, correlating learning material with student profiles. Our proposed model is validated through various performance metrics, showing significant improvements in student satisfaction and academic performance. Our contribution in the field of educational technology lies in proposing an efficient and scalable model for personalized learning experience, addressing the diversified needs of the students in the digital learning setting.