摘要
网页分类技术是Web数据挖掘的基础与核心,是基于自然语言处理技术和机器学习算法的一个典型的具体应用。基于统计学习理论和蚁群算法理论,提出了一种基于支持向量机和蚁群算法相结合的构造网页分类器的高效分类方法,实验结果证明了该方法的有效性和鲁棒性,弥补了仅利用支持向量机对于大样本训练集收敛慢的不足,具有较好的准确率和召回率。
Web page categorization is the foundation and core problem of web data mining,it is a typical application based on technology of natural language processing and machine learning.h is imperative to find an effective and efficient method for web page categorization.In this paper,a new method is proposed for web page categorization based on ant colony optimization algorithm(ACOA) and support vector machines(SVMs).The experimental results show that the method is effective and robust,only to make up for the use of support vector machines for large sample training set less than the slow convergence with better precision and recall.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第17期122-124,共3页
Computer Engineering and Applications
基金
2007年公安部应用创新计划项目(No.2007YYCIZXHNST063)~~
关键词
网页分类
蚁群算法
支持向量机
召回率
准确率
web page categorization
ant colony algorithm(ACA)
support vector machine(SVM)
recall
precision