Full Personalized Learning Path Recommendation: A Literature Review.

The widespread usage of online education has led to various learning activities, generating large amounts of data. A set of learning activities that assist users in achieving specific learning objectives make up a learning path. In innovative education applications, learning path recommendation is important because it can help students achieve their learning objectives more quickly, reduce the impact of information overload on students, and provide suitable sequences of learning resources for large numbers of online students. Furthermore, personalizing these learning paths has become a significant endeavor due to the learners’ diverse learning styles, backgrounds, and objectives. In this context, many researchers have proposed various approaches and methods for personalizing learning paths using data mining, machine learning, optimization and knowledge graph. The present paper thoroughly investigates and discusses these research works and the theoretical foundations of learning paths. Additionally, we emphasize the importance of introducing online and offline evaluation techniques within learning path approaches to help researchers better evaluate their works and deliver personalized and impactful educational experiences for students. Furthermore, we thoroughly examine the challenges related to learning path recommendation systems, emphasizing the need for significant consideration and resolution. By addressing these challenges, we can not only enhance personalization quality and develop high-quality, reliable, and effective systems but also uncover new avenues for research and innovation in this field.