基于事例推理的中文垃圾邮件过滤  

Chinese Spam Filtering Algorithms Based on Case Base Reasoning

作　　者：赵晶莹[1] 郭海[1] 王玲芬[1] 

机构地区：[1]大连民族学院计算机学院,辽宁大连116600

出　　处：《微电子学与计算机》2009年第12期64-66,共3页Microelectronics & Computer

基　　金：国家自然科学基金项目(60803096);国家民委项目(07DL07)

摘　　要：分析现有垃圾邮件过滤分类算法的不足,根据垃圾邮件的概念漂移特性,提出了一种基于CBR的垃圾邮件过滤算法.针对中文垃圾邮件特点提取特征,设计基于CRN网络的实例检索算法,该算法增加了预计算阶段,从而提高检索速度.实验结果表明,与传统贝叶斯算法相比,该算法对于动态变化的中文垃圾邮件数据集有更好的过滤效果.Considering concept drift of the spare, this paper analyzes the disadvantages of the spare filtering algorithms on use and pmposes a spare filtering algorithm based on CBR（Case-base Reasoning）. After identifying features of spare, this paper designs an alternative similarity retrieval algorithm based on Case Retrieval Nets （CRNs）, which has pre-computation phrase for speeding up retrieval . Experiments on the spain filtering algorithm have been presented and the results show that the algorithm achieves better performance of changing spain filtering compared with the traditional Bayes.

关 键 词：垃圾邮件过滤 实例推理 预计算实例检索网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]