基于支持向量机的Web分类  

Web Page Classification Based on Support Vector Machines

作　　者：曹振华[1] 贾银山[1] 王福威[1] 

机构地区：[1]辽宁石油化工大学计算机与通信工程学院,抚顺113001

出　　处：《微处理机》2010年第4期29-31,35,共4页Microprocessors

摘　　要：Web分类是在分析了网页的内容后,按照一定的规则将它分到一个或者多个合适的类别中去。支持向量机是在统计学习理论基础上发展起来的一种新的非常有效的机器学习方法。由于其出色的学习性能,该技术已成为分类领域新的研究热点。将支持向量机的理论应用到Web分类中,首先对网页进行了预处理,然后对网页文本进行特征提取和向量表示,最后将二叉树多分类支持向量机应用到Web分类中。通过实验对算法进行了验证,结果表明取得了良好的分类效果。Web page classification analyzes the web page contents and assigns it to one or more right categories according to certain rules. Support vector machine which is based on statistical learning theory has developed a new highly effective machine learning method. Because of its excellent learning perform- ance, the technology has become a new hotspot in the field of classification. Support vector machine is applied in the web page classification, firstly, the web pages are preprocessed, and then the page＇ s features are extracted and the pages are represented with feature vector, finally a binary tree multi - class support vector machine is applied to the web classification. The methods are verified by experiment results. The results show that the classification has achieved good results.

关 键 词：WEB分类 支持向量机 二叉树 

分 类 号：TP311.11[自动化与计算机技术—计算机软件与理论]