Integrating Research Analytic Framework and Personality Matching for Supervisor Recommendation

Supervisor selection is important for research students in their future studies and careers.Currently,students rely on information search or friends recommendation to find potential research supervisors.However,due to the challenges of incomplete and asymmetric information,students can hardly find suitable supervisors that match their research interests as well as personalities.Existing methods mainly consider topic-relevance and candidate-quality,and overlook the significance of connectivity consideration and two-sided matching degree of individuals personality styles.It proposes a novel supervisor recommendation approach that integrates relevance,connectivity,quality and personality-matching dimensions.The results of user-based evaluations demonstrate that the proposed approach generates more satisfactory recommendations as compared to that of all baseline methods.The present solution has been implemented as a social network recommendation service on ScholarMate.