摘要
随着Internet的飞速发展,Web文本分类研究已经得到了人们密切的关注,并取得了大量的研究成果。文中讨论了Web文本分类过程中的几个关键技术;针对传统的Web文本分类方法缺乏认知自主性和不能再学习的特点,提出了一种扩展的Web文本分类模型和算法。通过系列实验表明,该算法具有较高的分类精度和查准率。
With the development of Intemet at full speed,the research of Web text classification has already got people＇s close concem.A large amount of research results have been got. This paper has discussed several key technologies in the course of Web text classification in detail at first; Then directing against the traditional classification algorithm of Web text lack of cngnitive independence and studying again, it proposes an extended Web text classification model and algorithm. Through a series of experiments, can get the result that such algo- rithm has higher classification precision and recall.
出处
《计算机技术与发展》
2006年第3期116-118,共3页
Computer Technology and Development
关键词
WEB文本分类
向量空间模型
特征提取
反馈判定
Web text classification
vector space model
feature extraction
feedback and judge
