广义Web内容挖掘模型算法  

Models and algorithms for Web content mining in broad sense

作　　者：高宏 朱耀稷[1] 

机构地区：[1]天津大学管理学院,天津300072

出　　处：《天津理工大学学报》2005年第2期29-32,共4页Journal of Tianjin University of Technology

基　　金：天津市自然科学基金资助项目(043612211).

摘　　要：在信息时代的今天,网络以几何速度飞速发展,成为现代人获取信息的主要来源之一.也正因为网络信息增长太快,人们反而面临“信息爆炸”与“知识贫瘠”共存的局面.数据挖掘(DM)是通过数据获取知识的最佳工具,由此,产生了Web数据挖掘,即KDW的概念.本文重点论述广义Web内容挖掘的特点与发展、狭义的内容挖掘中页面内和页面间挖掘的区分及应用的主要算法、结构挖掘中的两大算法及其优劣.The network developing at the speed of geometry becomes one of main sources for the moderns to get information in this information age. Yet because the development speed is too high, the people face the situation of 'information explosion' and 'barren knowledge' coexisting. Data Mining is the best tool to obtain knowledge through data analysis and therefore the concept of KDW is produced. In this paper, the author mainly discusses Web Content Mining in broad sense, the differentiation between inside and outside web-page mining, main algorithms and their variants for web content mining in a narrow sense, and the good and bad points of two major algorithms in web structure mining.

关 键 词：广义Web内容挖掘 数据挖掘 DM 结构挖掘 算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]