ACRec: a co-authorship based random walk model for academic collaboration recommendation

Jing Li, Feng Xia, Wei Wang, Zhen Chen, Nana Yaw Asabere, Huizhen Jiang

Abstract: Recent academic procedures have depicted that work involving scientific research tends to be more prolific through collaboration and cooperation among researchers and research groups. On the other hand, discovering new collaborators who are smart enough to conduct joint-research work is accompanied with both difficulties and opportunities. One notable difficulty as well as opportunity is the big scholarly data. In this paper, we satisfy the demand of collaboration recommendation through co-authorship in an academic network. We propose a random walk model using three academic metrics as basics for recommending new collaborations. Each metric is studied through mutual paper co-authoring information and serves to compute the link importance such that a random walker is more likely to visit the valuable nodes. Our experiments on DBLP dataset show that our approach can improve the precision, recall rate and coverage rate of recommendation, compared with other state-of-the-art approaches.