网页自动分类技术概念分析.pdfVIP

5 2 V ol. 5 No. 2 2007 6 VocationalEducation and Econom ic Research Jun . , 2007 张 莉 ( , 621000) : 首先介绍和分析自动分类的种类和作用然后在分析网页特征的基础上介绍两种常用的网页识 别方 并研究其在网页分类应用中的现状, 列举几种常用的特征提取方 并比较其在网页分类应用中的优劣, 分析各种分类算 在网页分类的适用性并研究其发展和改进, 简述分类评价指标最后分析现有系统的特点 : 自动分类; 网页识别; 特征提取; 分类算 : TP3 3 : A : ( 2007) 02- 0058- 04 Ana ly sis ofW eb D ocum en ts C lassification T echn iques ZHAN G L i ( Southw estUn iversity of Science and Technology, M ianyang S ichuan 621000) A bstrac t: The k inds and functions of automatic classification are analyzed. A fter analyzing the fea tures ofw eb pages, wt o kinds of recognition methods are introduced and the application onw eb classi fication is studied. Several kinds of feature selection m ethods are listed and the effects of application on w eb classification are compared. The app licab ility on w eb of classifying algorithm s are analyzed and the developm ent and mi provement of algorithms are discussed. Evaluating indicators are listed. The paper endsw ith the analysis of the system s characteristics. K ey w ord s: automatic classification; recognition of w eb pages; feature selection; classifying algo rithm s , , , 2007 1 , , 44. 7 , , 20. 7, 86. 3% , , , , , , YAHOO, , 51. 5% , : 2007- 03- 20 : ( 1 82- ), , , 14 : 5 , , , URL , 1