Identifying a suitable supervisor for a new research student is vitally important for his or her academic career. Current information overload and information disorientation have posed significant challenges for new students. Existing research for supervisor identification focuses on quality assessment of candidates, but ignores indirect relevance with candidate supervisors' previous students, social network connections and their thinking styles. This paper presents a comprehensive student-centric approach based on research analytics framework for finding and recommending supervisors for new students. In particular, it integrates multiple measurements from three dimensions, ie, relevance, connectivity and quality. A prototype system was developed to support student-supervisor recommendations on a research social network platform (ie, ). The results of user-based evaluations demonstrate that our proposed approach generates more satisfactory recommendations as compared with that of all baseline methods. [ABSTRACT FROM AUTHOR]
© 2001-2024 Fundación Dialnet · Todos los derechos reservados