摘要
应用模糊c均值算法对文档进行分类,具有不使用语法知识、不使用词法规则、无监督等特点.采用模糊c均值算法对文档进行聚类,实验结果表明:该方法优于普通的聚类算法,聚类结果能充分体现文本的多样性.
The Fuzzy c-mean algorithm for document clustering has the features that exempt from grammar,word-formation heuristics, pre-segmented data and so on. The FCM(fuzzy c-mean algorithm) for document clustering has been discussed in this paper. The algorithm is superior to other general clustering algorithm and can be used in wide diversity of document.
出处
《长沙电力学院学报(自然科学版)》
2004年第4期12-14,共3页
JOurnal of Changsha University of electric Power:Natural Science
基金
湖南省教育厅科研基金资助项目(03C078)
关键词
文本聚类
模糊C均值算法
模糊聚类
document clustering
fuzzy C-mean algorithm
fuzzy clustering