摘要： 针对Web文档的特点,提出了一种多层向量空间模型,用来确定Web文档特征词的权重,然后给出了一种基于混合神经网络的文档聚类算法。实验结果表明,所提出的Web文档聚类算法具有较好的聚类特性,它能将与一个主题相关的Web文档较完全和准确地聚成一类。

关键词: 向量空间模型, 文档聚类, 自组织网络, 模糊C-Means

Abstract: A multi-level vector space model is proposed in this paper, the text weight is defined according to the model, a clustering algorithm based on the hybrid neural networks for Web document is presented. The experimental results show that the algorithm has good clustering performance, and the Web documents focusing on subject are rather completely and exactly clustering together.

中图分类号: 

• TP391.1