期刊文献+

基于学术会议的科研合作网络微观结构动态演化分析

Dynamic microscopic structure evolution analysis for the author collaboration network of academic conferences
下载PDF
导出
摘要 学术科研合作网络的演化特征研究,对掌握特定学术会议的发展有着重要的意义。目前主要针对合作网络的宏观特征演化进行分析,然而个体研究者的演化规律同样有着重要的作用。使用DBLP数据库系统提供的人工智能与模式识别领域的学术会议论文作者信息以及清华大学ArnetMiner系统下载的公用数据集作为原始数据,对合作发表论文形成的合作网络进行了研究。基于意见领袖和结构洞,从微观方面分析科研合作网络随时间发展的演化规律。实验结果表明:在给出的数据集上,以引用数作为意见领袖影响力衡量指标,按照PageRank值和度中心性指标比特征向量、接近中心性、介数中心性指标具有更好的刻画节点影响力的能力;在该网络演化过程中,结构洞变化相比于意见领袖的变化较稳定,每年占据结构洞的作者基本相同。结构洞的占据者大部分是意见领袖,并且这些作者在网络中占据结构洞的程度越来越大;且在网络演化过程中,结构洞占据者有可能成为意见领袖。 This paper makes an analysis on the author collaboration network of academic conferences. Based on the opinion leaders and structural holes,the evolution law of the collaboration network of academic conferences developing with time is analyzed from the microscopic view. The evolution characteristics of the academic author collaboration network have very important significance for grasping the development of the particular academic conferences. Currently,researchers mainly focus on the evolution analysis of macroscopic characteristics,but the evolution law of the individual researchers also plays an important role. Author information of conference papers in the field of artificial intelligence and pattern recognition provided by the Database systems and logic programming(DBLP) and the public datasets downloaded from the Arnet Miner system of Tsinghua University are taken as the original data. The experimental results show that in the given dataset,when using the number of citations as the index to measure the opinion leader,the indexes of PageRank and degree centrality are more capable of describing node 's influence than eigenvector,closeness centrality,betweenness centrality,and in the network evolution process. The change of structural hole is more stable than that of opinion leader,and the authors occupying structural holes are basically consistent each year. Most of structural hole occupiers are opinion leaders,also the ability of occupying structural holes is becoming better and better. In the process of network evolution,the structural hole occupiers are likely to be opinion leaders.
出处 《智能系统学报》 CSCD 北大核心 2015年第4期620-626,共7页 CAAI Transactions on Intelligent Systems
基金 国家自然科学基金资助项目(61175046 61402006) 安徽省自然科学基金资助项目(1508085MF113) 安徽省高等学校自然科学研究资助项目(KJ2013A016) 安徽大学国家级大学生创新创业训练计划资助项目(201410357041)
关键词 演化 科研合作网 意见领袖 结构洞 微观结构 PAGERANK 学术会议 引用数 evolution author collaboration network opinion leader structural hole microscopic structure PageRank academic conferences number of citations
  • 相关文献

参考文献21

  • 1De SOLLA P D S. Little science, big science [ M ]. New York: Columbia University Press, 1963.
  • 2NEWMAN M E J. The structure of scientific collaboration networks[ Jl. Proceedings of the National Academy of Sci- ences of the United States of America, 2001, 98( 2): 404- 409.
  • 3BARAB~SI AL, JEONG H, NI~DA Z, et al. Evolution of the social network of scientific collaborations [ J ]. Physica A: Statistical Mechanics and Its Applications, 2002, 311 (3/4) : 590-614.
  • 4TOMASSINI M, LUTHI L. Empirical analysis of the evolu- tion of a scientific collaboration network[ J ]. Physiea A: Sta-tistical Mechanics and Its Applications, 2007, 385 (2): 750-764.
  • 5PERC M. Growth and structure of Slovenia' s scientific col- laboration network [ J ]. Journal of Informetries, 2010, 4 (3) : 475-482.
  • 6RONDA-PUPO G A, GUERRAS-MARTIN L A. Dynamics of the scientific community network within the strategic man- agement field through the Strategic Management Journal 1980-2009: The role of cooperation [ J ]. Scientometrics, 2010, 85(3): 821-848.
  • 7KIM H, YOON J W, CROWCROFT J. Network analysis of temporal trends in scholarly research productivity [ J 1- Jour- nal of Informetrics, 2012, 6(1) : 97-110.
  • 8胡枫,赵海兴,何佳倍,李发旭,李淑玲,张子柯.基于超图结构的科研合作网络演化模型[J].物理学报,2013,62(19):539-546. 被引量:50
  • 9李季,汪秉宏,蒋品群,周涛,王文旭.节点数加速增长的复杂网络生长模型[J].物理学报,2006,55(8):4051-4057. 被引量:51
  • 10苑卫国,刘云,程军军.微博网络中用户特征量和增长率分布的研究[J].计算机学报,2014,37(4):767-778. 被引量:12

二级参考文献37

共引文献377

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部