ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2015, Vol. 52 ›› Issue (1): 156-166.doi: 10.7544/issn1000-1239.2015.20130915

• 软件技术 • 上一篇    下一篇

基于节点和信息特征的社会网络信息传播模型

周东浩1,2,韩文报2,3,王勇军1,   

  1. 1(国防科学技术大学计算机学院 长沙 410073); 2(数学工程与先进计算国家重点实验室 郑州 450002); 3(解放军信息工程大学 郑州 450002) (dhzhou2084@163.com)
  • 出版日期: 2015-01-01
  • 基金资助: 
    基金项目:国家“八六三”高技术研究发展计划基金项目(2009AA012201)

A Fine-Grained Information Diffusion Model Based on Node Attributes and Content Features

Zhou Donghao1,2,Han Wenbao2,3,Wang Yongjun1   

  1. 1(College of Computer, National University of Defense Technology, Changsha 410073); 2(State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450002); 3(PLA Information Engineering University, Zhengzhou 450002)
  • Online: 2015-01-01

摘要: 随着在线社会网络的快速发展,越来越多的人开始利用微博或Twitter来传播信息或分享观点.研究社会网络中的信息传播规律对于意见领袖挖掘、舆情监控、品牌营销等有着重要意义.虽然有关社会网络中的信息传播模型已经得到广泛研究,但是影响网络中节点之间信息传播的因素有哪些,以及如何刻画信息传播过程,仍然是一个有待深入研究的重要内容.传统的传播模型及其扩展模型更多地从网络结构出发研究信息传播,很大程度上忽视了节点属性和信息内容的影响.从多个维度提取信息传播的特征,包括节点属性特征和信息内容特征,对节点间传播概率和传播延迟进行建模,提出一个细粒度的在线社会网络信息传播模型.利用随机梯度下降算法学习模型中的各个特征的权重.另外,针对模型的传播预测功能,在新浪微博真实数据集上进行了实验,结果表明,在预测准确率方面,所提出的模型要优于其他同类模型,如异步独立级联模型、NetRate模型.

关键词: 社会网络, 信息传播, 传播模型, 节点属性, 传播预测

Abstract: With the development of online social networks, more and more people use Twitter or Weibo to propagate information or share opinions. Predicting the diffusion of information on social networks is a key problem for applications like opinion leader detection, public opinion monitoring or viral marketing. Although there has been extensive research on information diffusion model, what the factors that influence information diffusion are and how to characterize the process of information diffusion on social networks are still open problems. Traditional models pay more attention on network structures, and largely ignore important dimensions such as user attributes or information content features. In this paper, we extract features from multiple dimensions including node attributes and information contents, proposing a fine-grained information diffusion model based on these features. We use stochastic gradient descent method to learn the weights of these features in the proposed model, and then give quantitative analysis. Our model gives an insight into the extent on which these features can influence information diffusion on social network. Besides, given an initial state of information diffusion, our model can be used to predict the future diffusion process. Experiment results on Sina Weibo datasets show that the proposed model yields higher prediction precision than other widely used models like AsIC model or NetRate model.

Key words: social networks, information diffusion, diffusion model, node attribute, diffusion prediction

中图分类号: