Information Technology Reference
In-Depth Information
The Evaluation of Online Social Network's Nodes
Influence Based on User's Attribute and Behavior
Xiushuang Yi, Yeting Han, and Xingwei Wang
College of Information Science and Engineering Northeastern University Shenyang, China
xsyi@mail.neu.edu.cn
Abstract.
Objective and accurate assessment of each node influence is a vital
issue to research social networks. Many algorithms have been developed, but
most of them use of single metric, which is incomplete and limited to evaluate
node influence. In this paper, we propose a method of evaluating node influence
based on user's attribute and behavior. We study the quantification of nodes in-
fluence. The thought of PageRank is used to explore the effect of behavior.
Then the method proposed is applied to Sina micro-blog. Experiment results
show that method has a good and reasonable value.
Keywords:
social networks, node influence, PageRank, node attribute.
1
Introduction
In last ten years, the numbers of online social networks like Facebook, MySpace and
Twitter gained considerable popularity and grown at an unprecedented rate. The
emergence of online social networks has brought great convenience to people's life.
One of the main applications of online social networks can help manufacturers to
promote their products, and to utilize the lowest investment cost to achieve the maxi-
mum effectiveness of marketing. Therefore, online social networks have also attracted
many scholars to study it. A part of scholars focus on the influence of online social
networks nodes, more and more interests have been made in obtaining information
from social networking websites for analyzing people behaviors. These researches are
focusing on identifying the influential social network users, so it can help to increase
the marketing efficiency, and also can be utilized to gather opinions and information
on particular topics as well as to predict the trends [1-3].
Micro-blog is a typical online social network, it not only has the social network
characteristics but also has the media characteristics, so it can be analyzed from social
networks and news dissemination, how to find influential micro-blog is a basic
problem in the research and application of microblog.A lot of micro-blog application
use "micro-blog numbers", "number of fans", "attention", "forward", as the ranking
basis. These indicators can only measure the nodes from one aspect. These indexes not
only can't help the user to find the influence of micro-blog quickly, but also can not
truly reflect the actual influence of micro-blog users in the network. In order to
overcome these shortcomings, we try to present a new method to evaluate node
influence.
