节点文献
基于非负因子分析的模糊文本挖掘
Fuzzy text mining based on nonnegative factor analysis
【Author】 ZHU Qiang-Sheng, TIANYing , ZHOU Yan-Quan, HE Hua-Can (Research Center of Intelligent Sciences and Technology, Beijing University of Post and Telecommunication, Beijing 1000876, China) (College of Science, China Agricultural University, Beijing, 100094, China)
【机构】 北京邮电大学智能科学技术研究中心; 中国农业大学理学院数学组;
【摘要】 文本聚类是目前文本挖掘中重要的探索性数据分析方法。一篇文档仅属于某个主题,是很不现实的,所以模糊文本聚类比一般的硬文本聚类更科学。本文借助于非负矩阵分解算法,提出了一种基于非负因子分析的模糊文本聚类方法。
【Abstract】 As an exploratory data analysis method, text clustering is very important in text mining. Just as we know, there seldom exists document that only belongs to one topic, so fuzzy text clustering methods are more scientific than those crisp ones. Inspired by the nonnegative matrix factorization algorithm, we put forward an fuzzy text clustering method based on nonnegative factor analysis.
【Key words】 text clustering; fuzzy C-means; nonnegative factor analysis; nonnegative matrix factorization;
- 【会议录名称】 2006通信理论与技术新进展——第十一届全国青年通信学术会议论文集
- 【会议名称】第十一届全国青年通信学术会议
- 【会议时间】2006-07
- 【会议地点】中国四川绵阳
- 【分类号】TP311.13
- 【主办单位】中国通信学会青年工作委员会