Recommendation of leaders in online social systems

  • Authors:

  • Hao Liu;Fei Yu;An Zeng;Linyuan Lü

  • Affiliations:

  • Institute of Information Economy, Hangzhou Normal University, Hangzhou, People's Republic of China, Department of Physics, University of Fribourg, Fribourg, Switzerland;Department of Physics, University of Fribourg, Fribourg, Switzerland;Department of Physics, University of Fribourg, Fribourg, Switzerland;Institute of Information Economy, Hangzhou Normal University, Hangzhou, People's Republic of China, Department of Physics, University of Fribourg, Fribourg, Switzerland

  • Venue:
  • ISMIS'12 Proceedings of the 20th international conference on Foundations of Intelligent Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The online social systems are now playing a more and more important role in our daily life. Information coming from such systems is more personalized and preferable than those from search engines and portals. Those systems are normally described by directed networks where the nodes represent users and the information spreads from leaders to followers. Therefore, the selection of suitable leaders determines the quality of the coming information. In this paper, we propose a leader recommendation method based on a local structure consisting of 4 nodes and 3 directed links. The simulation results on real networks show that our method can accurately recommend the potential leaders. Moreover, further investigation on recommendation diversity indicates that our recommendation method is very personalized. Finally, we remark that our method can be easily extended to improve the existing link prediction algorithms in directed networks.