A Novel Method of Identifying Influential Users on Social Network
- DOI
- 10.2991/itms-15.2015.173How to use a DOI?
- Keywords
- Social network; Influential nodes; Structural holes
- Abstract
Identifying the influential users on social network is a critical problem for advertising, promotion, public opinion analysis and network security. A few empirical studies have verified that some users could lead to wider spreading and promote the information diffusion prominently. However, the existing studies limited by a single layer analysis for information diffusion, there is still lack of a multifaceted analysis method for identifying influential nodes. In this paper, we propose a novel method for identifying the influential users in the topology of information diffusion, which contains a three-tier analytical mechanism: information-level analysis, relationship-level analysis and community-level analysis. This three-tier analytical mechanism can upgrade information-level to relationship-level, and finally identifying the influential nodes in relationship-level. The experiments on Sina Weibo demonstrate that 0.3% of users who span structural holes control 28% of the information diffusion in each event and can cause the secondary-wave of information diffusion. When the information diffuses to users with higher pagerank, more users will participate in the information diffusion.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Jingchi Jiang AU - Wenchong Bi AU - Chengqi Yi AU - Yuanyuan Bao AU - Yibo Xue PY - 2015/11 DA - 2015/11 TI - A Novel Method of Identifying Influential Users on Social Network BT - Proceedings of the 2015 International Conference on Industrial Technology and Management Science PB - Atlantis Press SP - 733 EP - 736 SN - 2352-538X UR - https://doi.org/10.2991/itms-15.2015.173 DO - 10.2991/itms-15.2015.173 ID - Jiang2015/11 ER -