Personalized Services for Students in a Smart Campus Through Hybrid Recommendations

Abstract

The advancement of AI and pervasive technologies is reshaping intelligent environments, enabling digital systems to adapt to users’ specific needs. In the academic domain, students navigate complex digital and physical spaces where the lack of personalized support can lead to inefficiencies in decision-making and underutilization of resources. This paper presents novel context-aware hybrid recommendation framework for Smart Campus environments that seamlessly integrates data from IoT sensors, personal smart devices, and user profiles through advanced AI techniques. By integrating hybrid collaborative and content-based filtering with Transformer-based language models, the proposed system provides dynamic, personalized recommendations for study groups, subjects, and thesis topics, thereby enhancing student engagement and optimizing campus resource utilization. Preliminary evaluations conducted on two real-world datasets demonstrate that the proposed approach achieves superior recommendation accuracy compared to state-of-the-art models. These results highlight its potential to transform campuses into more engaging and supportive environments, paving the way for a new generation of user-centered services.