图书情报工作 ›› 2019, Vol. 63 ›› Issue (4): 135-141.DOI: 10.13266/j.issn.0252-3116.2019.04.016

• 综述述评 • 上一篇    下一篇

用于科学结构分析的混合网络社团划分方法述评

张瑞红1,2, 陈云伟1,2, 邓勇1,2   

  1. 1. 中国科学院成都文献情报中心 科学计量与科技评价研究中心(SERC) 成都 610041;
    2. 中国科学院大学经济与管理学院图书情报与档案管理系 北京 100190
  • 收稿日期:2018-05-21 修回日期:2018-09-26 出版日期:2019-02-20 发布日期:2019-02-20
  • 通讯作者: 邓勇(ORCID:0000-0001-9179-0500),研究员,硕士生导师,通讯作者,E-mail:dengy@clas.ac.cn
  • 作者简介:张瑞红(ORCID:0000-0001-5786-4182),硕士研究生;陈云伟(ORCID:0000-0002-6597-7416),研究员,硕士生导师。
  • 基金资助:
    本文系国家重点研发计划现代服务业重点专项"专业内容知识服务众智平台与应用示范"(项目编号:2017YFB1402400)研究成果之一。

A Review of Community Discovery in Hybrid Network for Science Structure Analysis

Zhang Ruihong1,2, Chen Yunwei1,2, Deng Yong1,2   

  1. 1. Scientometrics & Evaluation Research Center(SERC), Chengdu Library and Information Center of Chinese Academy of Sciences, Chengdu 610041;
    2. Department of Library, Information and Archives Managment, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190
  • Received:2018-05-21 Revised:2018-09-26 Online:2019-02-20 Published:2019-02-20

摘要: [目的/意义]复杂网络的社团结构研究已逐渐成为科学家借助文献数据开展科学结构研究的有力工具,社团划分效果的不同对科学结构的解读有着举足轻重的影响。本文对混合网络社团划分方法进行梳理,以期对该领域的相关研究提供借鉴参考。[方法/过程]通过文献调研,阐明混合网络的概念与类型,从网络构建或算法革新角度对各类型混合网络的社团划分研究进行概述,也对支撑混合网络社团划分的经典算法进行简介。[结果/结论]通过系统地梳理总结不同类型混合网络的社团划分工作,为后续的网络分析研究提供研究的视角和方法,同时揭示其在科学结构研究中所面临的挑战与所具有的现实意义,展望今后可能进一步拓展的相关研究方向。

关键词: 混合网络, 社团划分, 聚类分析, 合作, 引用

Abstract: [Purpose/significance] The study of community structure of complex networks has gradually become a powerful tool for scientists to carry out scientific structure research with literature data. In addition, the different results of community discovery play an important role in the interpretation of scientific structure. Therefore, this paper sorts out the methods of community discovery in hybrid networks, in order to provide reference and expand the ideas for the relevant researchers in the field. [Method/process] Through literature research, this paper mainly clarifies the concept and types of hybrid networks, and summarizes the research on community discovery of various types of hybrid networks from the perspective of network construction or algorithm innovation. Furthermore, the classical algorithm for supporting hybrid networks community discovery is also introduced. [Result/conclusion] Through the systematic review of the community discovery of different types of hybrid networks, it provides a new perspective and method for subsequent network analysis research, meanwhile reveals the challenges and practical significance of its research in scientific structure. Finally this paper also looks forward to relevant research directions that may be further expanded in the future.

Key words: hybrid network, community discovery, clustering, collaboration, citation

中图分类号: