摘要
中文网页分类技术是数据挖掘中一个研究热点领域,而支持向量机(SVM)是一种高效的分类识别方法,在解决高维模式识别问题中表现出许多特有的优势。提出了基于支持向量机的中文网页分类方法,其中包括对该过程中的网页文本预处理、特征提取和多分类算法等关键技术的介绍。实验表明,该方法训练数据规模大大减少,训练效率较高,同时具有较好的精确率和召回率。
Chinese web page classification has been considered as a hot research area in data mining. SVM is an effective method for learning the classification knowledge from massive data, especially in the situation of high cost in getting labeled classical examples. Based on the analyses of features of Chinese web pages, A Chinese web page classification algorithm based on SVM is presented to effectively organize the rich information on the Internet, including the important aspects of text preprocessing, feature selection and multiple-class algorithm. The experiments show that it not only reduces the size of train set, but also has very high training efficiency. Its precision and recall are also very good.
出处
《计算机工程与设计》
CSCD
北大核心
2007年第8期1893-1895,共3页
Computer Engineering and Design
基金
中国矿业大学青年科研基金项目(OD4490)
关键词
支持向量机
特征提取
核函数
网页
文本分类
support vector machine
feature selection
kernel function
web page
text classification
