基于主题概念实现对购物网站的自动主题分类  

AUTOMATICALLY CLASSIFYING TOPIC ON ONLINE SHOPPING WEBSITES USING THEME-BASED CONCEPT

作　　者：陈洪平[1] 方巍[1] 黄黎[1] 崔志明[1] 

机构地区：[1]苏州大学智能信息处理及应用研究所,江苏苏州215006

出　　处：《计算机应用与软件》2010年第9期9-10,45,共3页Computer Applications and Software

基　　金：国家自然科学基金项目(60673092);2008年江苏省重大科技支撑与自主创新项目(BE2008044);2006年度江苏省软件和集成电路业专项经费项目([2006]221-41);2006江苏省"六大人才高峰"项目(06-E-037)

摘　　要：基于传统的关键词统计的分类方法难以正确识别网页的主题,从而难以实现按主题进行分类。为了有效地对Web上的结构化数据源进行主题分类,结合语义知识,将基于概念的主题分类方法,应用到网络购物网站数据源的自动主题分类中。实验表明,该方法能够较好地提高主题分类的精度。The classification methods based on traditional key words statistics are hard to classify webpage according to its topic due to poor in detecting the topics of the webpage. In order to solve topic classification on structured web data sources effectively, in this paper the seman- tic knowledge is taken into account, and the concept-based topic classification method is applied to automatic topic classification of data sources of online shopping websites. Experimental results show that the method can gain a high precision in topic classification.

关 键 词：本体 主题 网页分类 

分 类 号：TP393.092[自动化与计算机技术—计算机应用技术]