A Knowledge Graph Embedding Based Approach for Learning Path Recommendation for Career Goals

Abstract

Nowadays, many online courses in the Information Technology (IT) field provided by different organizations make it difficult for learners to screen the courses that are best suitable for their career development. Many approaches have been raised to suggest a personalized learning path based on the learner’s career goals; however, most of them use traditional techniques and face the problems of sparse data, cold start, and lack of advisory results’ interpretation. In this paper, we address these problems by using Knowledge Graph Embedding (KGE) which is known as one of approaches of Graph-based models. This approach has emerged as a phenomenon and has not been widely applied in the field of learning path recommendation. We propose a new knowledge graph (KG) architecture for representing entities and their semantic relationships. The main entities identified in the KG are courses, occupations, the units of knowledge, and the relationships are the semantic connections between these entities. In existing KG architectures only exploit the hierarchy of intermediate knowledge units. Whereas, our KG architecture provides a specific classification of these learning objects, and this helps the semantic relationship of the subjects become more unambiguous and connected. Then, we explore and build experiments for our proposed KG architecture by using KGE techniques to prove the effectiveness. The experimental results show that our solution is worth considering and promises to bring a high degree of efficiency in the learning path recommendation system.