图书情报工作

图书情报工作 >

2014 , Vol. 58 >Issue 23: 129 - 135

DOI: https://doi.org/10.13266/j.issn.0252-3116.2014.23.020

知识组织

社会化标注环境下的标签共现谱聚类方法

  • 李慧宗 ,
  • 胡学钢 ,
  • 何伟 ,
  • 潘剑寒
展开
  • 1. 合肥工业大学计算机与信息学院;
    2. 安徽理工大学经济与管理学院
李慧宗, 合肥工业大学计算机与信息学院博士研究生, 安徽理工大学经济与管理学院副教授, E-mail:lihz_aust@sina.com;胡学钢, 合肥工业大学计算机与信息学院教授, 博士生导师;何伟, 合肥工业大学计算机与信息学院博士研究生;潘剑寒, 合肥工业大学计算机与信息学院博士研究生.

收稿日期: 2014-09-24

  修回日期: 2014-11-20

  网络出版日期: 2014-12-05

基金资助

本文系国家自然科学基金项目"基于协同训练策略的不完全标记数据流分类问题研究"(项目编号:61273292)和教育部人文社会科学研究青年基金项目"社会化标注环境下的标签层次关系发现方法研究"(项目编号:13YJCZHO77)研究成果之一.

收起

Tags Co-occurrence Spectral Clustering Method in Social Tagging Environment

  • Li Huizong ,
  • Hu Xuegang ,
  • He Wei ,
  • Pan Jianhan
Expand
  • 1. School of Computer and Information, Hefei University of Technology, Hefei 230009;
    2. School of Economics and Management, Anhui University of Science and Technology, Huainan 232001

Received date: 2014-09-24

  Revised date: 2014-11-20

  Online published: 2014-12-05

Fold

摘要

在分析标签共现的基础上, 提出一种基于共现的标签谱聚类方法, 该方法直接利用标签的共现关系来测度标签的相关性, 能够避免将标签表示成向量空间模型时所带来的高维稀疏等问题.在衡量标签的共现相似性时, 设计一种综合的方法, 并给出标签综合共现相似度的计算公式.与传统的单一利用标签的个体共现来衡量其相似性相比, 综合的方法同时考虑标签的个体共现相似性和标签的群体共现相似性, 能够更加精确地刻画标签的共现相似度.实验结果表明, 基于综合共现相似度的标签共现谱聚类方法具有较好的效果.

关键词： 社会化标签系统; 标签共现; 谱聚类; 相似性

本文引用格式

李慧宗 , 胡学钢 , 何伟 , 潘剑寒 . 社会化标注环境下的标签共现谱聚类方法[J]. 图书情报工作, 2014 , 58(23) : 129 -135 . DOI: 10.13266/j.issn.0252-3116.2014.23.020

Abstract

Based on analyzing the tags co-occurrence, a tags co-occurrence spectral clustering method is presented. The method utilizes the co-occurrence relations of tags to measure their correlation, which could avoid the high dimensional and sparse problems when the tag is represented as vector space model. An integrated approach is designed when co-occurrence similarity among tags is measured, and the tag integrated co-occurrence similarity calculation formula is given. Compared with the traditional approach which uses the individual co-occurrence of tags to measure their similarity singly, the integrated approach considers not only the tag individual co-occurrence similarity, but also the tag common co-occurrence group similarity, which could precisely characterize the similarity among tags. Experimental results show that the tag co-occurrence spectral clustering method based on integrated co-occurrence similarity has a better effect.

Key words： social tagging system; tag co-occurrence; spectral clustering; similarity

参考文献

[1] Isabella P.Folksonomies:Indexing and retrieval in Web 2.0[M]. Berlin:De Gruyter Saur, 2009:369-374.
[2] 罗鹏程, 陈翀.从大众分类到层次式资源组织体系——利用聚类信息构建标签树[J].图书情报工作, 2013, 57(22):120-125.
[3] Cuzzocrea A.Combining multidimensional user models and knowledge representation and management techniques for making Web services knowledge-aware[J].Web Intelligence and Agent Systems, 2006, 4(3):289-312.
[4] 易明, 操玉杰, 沈劲枝, 等.社会化标签系统中基于密度聚类的Web用户兴趣建模方法[J].情报学报, 2011, 30(1):37-43.
[5] Shepitsen A, Gemmell J, Mobasher B, et al.Personalized recommendation in social tagging systems using hierarchical clustering[C] // Proceedings of the 2008 ACM Conference on Recommender Systems.New York:ACM, 2008:259-266.
[6] Xu Guandong, Zong Yu, Jin Ping, et al.KIPTC: A kernel information propagation tag clustering algorithm[J].Journal of Intelligent Information Systems, 2013:1-18.
[7] Knautz K, Soubusta S, Stock W G.Tag clusters as information retrieval interfaces [C] // Proceedings of the 43rd Hawaii International Conference on System Sciences.Big Island, Hawaii:IEEE Computer Society Press,2010:1-10.
[8] Begelman G, Keller P, Smadja F.Automated tag clustering:Improving search and exploration in the tag space [C] // Collaborative Web Tagging Workshop at WWW2006.Edinburgh:ACM, 2006:15-33.
[9] Cui Jianwei, Liu Hongyan, He Jun, et al.Tagclus:A random walk-based method for tag clustering[J].Knowledge and Information Systems, 2011, 27(2):193-225.
[10] 王萍, 张际平.一种社会性标签聚类算法[J].计算机应用与软件, 2010, 27(2):126-129.

Options
文章导航

/

〈 〉