作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (16): 263-266. doi: 10.3969/j.issn.1000-3428.2012.16.069

• 开发研究与设计技术 • 上一篇    下一篇

基于相似性链路预测的大众生产演化特征

姚灿中 1,杨建梅 2   

  1. (1. 华南理工大学经济与贸易学院,广州 510006;2. 华南理工大学工商管理学院,广州 510640)
  • 收稿日期:2011-09-28 修回日期:2011-12-06 出版日期:2012-08-20 发布日期:2012-08-17
  • 作者简介:姚灿中(1983-),男,讲师、博士,主研方向:复杂系统,复杂网络;杨建梅,教授、博士、博士生导师
  • 基金资助:
    国家自然科学基金资助项目(71173076, 71103044);中央高校基本科研业务费基金资助项目(2011ZB0011);广东省哲学社会科学“十一五”规划基金资助项目(07GO02)

Evolution Characteristic of Peer Production Based on Similarity Link Prediction

YAO Can-zhong 1, YANG Jian-mei 2   

  1. (1. School of Economics and Commerce, South China University of Technology, Guangzhou 510006, China; 2. School of Business Administration, South China University of Technology, Guangzhou 510640, China)
  • Received:2011-09-28 Revised:2011-12-06 Online:2012-08-20 Published:2012-08-17

摘要: 结合大众生产虚拟社区的静态结构与动态演化机理,提出择优机制与间接推荐是大众生产虚拟社区的显著演化特征。针对Wiki票选管理员的行为网络进行分析,结果显示虚拟社区贡献者的选择行为具有较强异质性特征。采用基于局部信息相似性的链路预测方法对网络潜在链接特征进行分析,得出择优指标值在各项指标中得分最高的结果。运用基于路径相似性的链路预测方法,证明相比其他路径与随机游走指标,Katz指标有更好的预测结果,说明间接推荐是虚拟社区演化过程的重要特征。

关键词: 大众生产, 虚拟社区, 复杂网络, 链路预测, 幂律分布, 择优机制

Abstract: This paper reveals the preferred mechanism is a significant evolution characteristic of peer production virtual community by the analysis on static structure and dynamic evolution of virtual community. It analyzes the cooperation network of peer production virtual community based on Wiki voting administrators behaviors. The result shows that the contributors behave heterogeneously. It applys the link prediction method based on local information similarity to analyze the potential connection of the network, and finds the preferred mechanism plays an important role in the network formation process. It uses the link prediction method based on path and random walk similarity to analyze the network and reveal Katz index performs better than other indices, and concludes that besides the preferred mechanism, the indirect recommendation is another important evolution characteristic of virtual communities.

Key words: peer production, virtual community, complex network, link prediction, power law distribution, preferred mechanism

中图分类号: