Leveraging Knowledge Graphs for Personalized Internship Recommendations: A Case Study on Software Engineering Courses
Supitsara Seetaworn, Phuree Phenhiran, Perapard Ngokpol, Montira Innoy, Sorayuth Ingboon, Tharathon Utasri, Akkharawoot Takhom · 2025
Internships play a vital role in bridging academic learning with industry requirements. This paper presents a knowledge graph-based framework for generating personalized internship recommendations by integrating course syllabi, student competencies, and job descriptions. The approach leverages structured knowledge representation and graph traversal to dynamically match students' academic progress with relevant opportunities. Additionally, Large Language Models (LLMs) are employed for entity extraction to enhance recommendation accuracy. A case study involving Software Engineering subjects within a Programme of Innovative Engineering demonstrates the framework's ability to provide tailored internship suggestions and identify skill gaps. The results indicate that knowledge graphs offer a scalable and adaptable solution for aligning academic curricula with evolving industry needs.