摘要
对海量数据进行聚类,从中获取有价值的隐含知识,已经成为一项迫切的需求。传统的基于词频或距离的文本聚类技术在准确度方面存在较大差距。引入文本语义信息的聚类方法,提高了聚类的准确度。实验结果表明,基于语义特征的模糊聚类算法具有较好的聚类效果。
Cluster of massive data, gain valuable implicit knowledge, has become an urgent demand. A wide gap between traditional texts clustering technique based on word frequency or distance exists. Using the text semantic information clustering methods improve the accuracy of clustering. This method implements word clustering by calculating text semantic information. The experiments show that the proposed method clustering trends to perform better than the traditional method.
出处
《信息技术》
2014年第12期121-123,128,共4页
Information Technology
基金
辽宁省社科联2014年度辽宁经济社会发展立项课题(2014LSLKTDGLX-02)
