基于混合聚类的中文词聚类

文本聚类在文本挖掘和信息检索系统中发挥着重要的作用,而词聚类是文本聚类的基础。提出了一种基于混合聚类的中文词聚类方法,它将层次聚类和概念聚类结合起来,以缩短整个聚类时间。首先对预处理后的词集进行初始聚类,然后从每个类中各取一个出现次数最多的词组成新的词集,最后对该词集进行再聚类。实验表明,这种方法有效降低了中文词聚类的时间复杂度。

Chinese Word Clustering Based on hybrid Clustering

Text clustering based on word clustering plays an important role in text mining and information search system.A Chinese word clustering method based on hybrid clustering was proposed,which conjugates hierarchical clustering and conceptual clustering to reduce the whole clustering time.The method firstly clustered word set which had been pretreated,and then used the words whose occurence number was maximum in each cluster to compose a new word set.In the end,the new word set was clustered again.The experimen...