图书情报工作 ›› 2020, Vol. 64 ›› Issue (8): 134-140.DOI: 10.13266/j.issn.0252-3116.2020.08.015

• 知识组织 • 上一篇    下一篇

基于谱聚类的虚拟健康社区知识聚合方法研究

张海涛1,2, 宋拓1, 周红磊1, 张鑫蕊1   

  1. 1 吉林大学管理学院 长春 130022;
    2 吉林大学信息资源研究中心 长春 130022
  • 收稿日期:2019-09-01 修回日期:2019-11-12 出版日期:2020-04-20 发布日期:2020-04-20
  • 作者简介:张海涛(ORCID:0000-0002-9421-8187),教授,博士生导师,E-mail:zhtinfo@126.com;宋拓(ORCID:0000-0003-1282-1861),博士研究生;周红磊(ORCID0000-0002-9732-8138),硕士研究生;张鑫蕊(ORCID:0000-0001-9413-6109),硕士研究生。

Research on Knowledge Aggregation Method of Virtual Healthy Community Based on Spectral Clustering

Zhang Haitao1,2, Song Tuo1, Zhou Honglei1, Zhang Xinrui1   

  1. 1 School of Management, Jilin University, Changchun 130022;
    2 Jilin University Information Resource Research Center, Changchun 130022
  • Received:2019-09-01 Revised:2019-11-12 Online:2020-04-20 Published:2020-04-20

摘要: [目的/意义] 改善虚拟健康社区知识聚合质量,为虚拟健康社区服务提供技术方法支持。[方法/过程] 运用谱聚类方法对虚拟健康社区中的知识进行抽取,利用概念相似度计算得到知识主题相似度矩阵,根据该相似度矩阵进行谱聚类。[结果/结论] 利用好大夫在线健康咨询平台发布的信息作为数据来源进行方法验证。结果表明,当聚类个数为5时,本文提出的方法得分值最高。通过谱聚类的方法充分挖掘虚拟健康社区潜在信息,改善了知识聚合质量,为知识聚合和知识服务提供了一条新途径。

关键词: 虚拟健康社区, 知识聚合, 谱聚类, 相似度

Abstract: [Purpose/significance] To improve the quality of knowledge aggregation in healthy virtual communities and provide technical method support for virtual healthy community services. [Method/process] The method of spectral clustering was applied to knowledge in the virtual healthy community was extracted, and the semantic similarity matrix of the text was obtained by using the keyword co-occurrence. The spectral clustering was performed according to the text semantic similarity matrix, and the text was aggregated into text clusters. [Result/conclusion] The information published by the doctor’s online health consultation platform was used as a data source for method validation. The results show that when the number of clusters is 5, the proposed method has the highest score. This method of spectral clustering considers the semantic relationship between words, fully exploits the potential information of virtual healthy community, improves the quality of knowledge aggregation, and provides a new way for knowledge aggregation and knowledge service.

Key words: virtual healthy community, knowledge aggregation, spectral clustering, similarity

中图分类号: