Finding appropriate experts for collaboration

  • Authors:

  • Zhenjiang Zhan;Lichun Yang;Shenghua Bao;Dingyi Han;Zhong Su;Yong Yu

  • Affiliations:

  • Shanghai Jiao Tong University, Shanghai, China;Shanghai Jiao Tong University, Shanghai, China;IBM China Research Laboratory, Beijing, China;Shanghai Jiao Tong University, Shanghai, China;IBM China Research Laboratory, Beijing, China;Shanghai Jiao Tong University, Shanghai, China

  • Venue:
  • WAIM'11 Proceedings of the 12th international conference on Web-age information management
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In our daily life, people usually want to find someone to collaborate with for the purpose of information sharing or work cooperation. Studies show social relationships play an important role in people's collaborations. Therefore, when finding appropriate experts for a user, two aspects of an expert candidate should be considered: the expertise and the social relationship with the user. One basic model is to filter out expert candidates by one aspect and rank them by the other (FOM). Another basic model tries to combine them using linear combination method (LCM). Both models as baselines here fail to exploit the intrinsic characteristic of social relationships for the tradeoff between two above aspects. In this paper, we formally define two factors respectively (i.e., expert authority and closeness to user) and propose a novel model called friend recommendation model (FRM) which tightly combines both factors in a natural friend recommendation way and is formalized by probability and Markov Process theories. Experiments were carried out in a scenario that a user looks for coauthors in the academic domain. We systematically evaluated the performances of these models. Experimental results show FRM outperforms other two basic models in finding appropriate experts.