用于垃圾邮件的贝叶斯过滤算法研究  

Research of a spam filter based on improved naive Bayes algorithm

作　　者：曹翠玲 王媛媛[2] 袁野[1] 赵国冬[1] CAO Cui-ling WANG Yuan-yuan YUAN Ye ZHAO Guo-dong(College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China)

机构地区：[1]哈尔滨工程大学计算机科学与技术学院,黑龙江哈尔滨150001 [2]东北林业大学机电工程学院,黑龙江哈尔滨150040

出　　处：《网络与信息安全学报》2017年第3期64-70,共7页Chinese Journal of Network and Information Security

摘　　要：研究了基于改进的支持向量机(SVM,support vector machine)算法结合朴素贝叶斯算法在垃圾邮件过滤中的应用。首先,SVM对训练集样本空间中两类交界处的集合构造一个最优分类超平面;然后,每个样本根据与其最近邻的类型是否相同进行取舍,从而降低样本空间也提高了每个样本类别的独立性;最后,利用朴素贝叶斯算法对邮件分类。仿真实验结果表明,该算法降低了样本空间复杂度,快速得到最优分类特征子集,有效地提高了垃圾邮件过滤的分类速度、准确率和召回率。In spam filtering filed, naive Bayes algorithm is one of the most popular algorithm, a modified using support vector machine（SVM） of the native Bayes algorithm ：SVM-NB was proposed. Firstly, SVM constructs an optimal separating hyperplane for training set in the sample space at the junction two types of collection, Secondly, according to its similarities and differences between the neighboring class mark for each sample to reduce the sample space also increase the independence of classes of each samples. Finally, using naive Bayesian classification algorithm for mails. The simulation results show that the algorithm reduces the sample space complexity, get the optimal classification feature subset fast, improve the classification speed and accuracy of spam filtering effectively.

关 键 词：朴素贝叶斯 支持向量机 修剪 垃圾邮件 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]