A Spam Filtering Algorithm Based on Conditional Entropy

doi:10.3969/j.issn.1006-2475.2014.02.030

Abstract

Abstract: In spam filtering, according to the filter misjudgment for legitimate mails, we put forward an improved spam filtering algorithm, which improves the conditional entropy estimation method of information gain. Combined with the Bayes minimum risk decision method, we analyze the algorithm through the recall and accuracy by carrying out an experiment on the English Corpus. Experimental results show that the improved algorithm can enhance the classification precision and reduce the misjudgment of legitimate emails, which can reduce the loss of users.

Key words: spam, information gain, conditional entropy, minimum risk

CLC Number:

TP391

ZHAI Jun-chang1, CHE Wei-wei2.

A Spam Filtering Algorithm Based on Conditional Entropy

[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2014.02.030.

References 15

[1]	黄国伟,许昱玮. 基于用户反馈的混合型垃圾邮件过滤方法[J]. 计算机应用, 2013,33(7):1861-1865.
[2]	邓维斌,王国胤,洪智勇. 基于粗糙集的加权朴素贝叶斯邮件过滤方法[J]. 计算机科学, 2011,38(2):218-221.
[3]	Sanchez F, Duan Z, Dong Y. Understanding forgery properties of spam delivery paths[C]// Proceedings of the 7th Annual Conference on Collaboration, Electronic Messaging, Anti-Abuse and Spam. 2010.
[4]	陈孝礼,刘培玉. 应用于垃圾邮件过滤的词序列核[J]. 计算机应用, 2011,31(3):698-701.
[5]	Sahami M, Dumais S, Heckerman D, et al. A Bayesian approach to filtering junk e-mail[C]// Proceedings of the 1998 AAAI Workshop on Learning for Text Categorization. 1998:55-62.
[6]	Androutsopoulos I, Koutsias J, Chandrinos K V, et al. An evaluation of naive Bayesian anti-spam filtering[C]// Proceedings of the 11th European Conference on Machine Learning. 2000:9-17.
[7]	Metsis V, Androutsopoulos I, Paliouras G. Spam filtering with naive Bayes: Which naive Bayes?[C]// Proceedings of the 3rd Conference on Email and Anti-Spam. 2006.
[8]	Chen Bin, Dong Shoubin, Fang Weidong. Introduction of fingerprint vector based Bayesian method for spam filtering[C]// Proceedings of the 4th Conference on Email and Anti-Spam. 2007.
[9]	翟军昌,秦玉平,车伟伟. 应用特征词分类贡献的垃圾邮件过滤研究[J]. 计算机工程与应用, 2012,48(34):116-119,170.
[10]	薛正元. 基于改进贝叶斯决策的邮件过滤[J]. 计算机工程与应用, 2013,49(7):98-101,125.
[11]	梁志文,杨金民,李元旗. 基于多项式模型和低风险的贝叶斯垃圾邮件过滤算法[J]. 中南大学学报:自然科学版, 2013,44(7):2787-2792.
[12]	陶永才,薛正元,石磊. 基于MapReduce的贝叶斯垃圾邮件过滤机制[J]. 计算机应用, 2011,31(9):2412-2416.
[13]	夏超,徐德华. 一种改进的贝叶斯邮件过滤算法[J]. 计算机与现代化, 2010(10):125-128,132.
[14]	Guzella T S, Caminhas W M. A review of machine learning approaches to spam filtering[J]. Expert Systems with Applications, 2009,36(7):10206-10222.
[15]	Lai Chih-chin. An empirical study of three machine learning methods for spam filtering[J]. Knowledge-based Systems, 2007,20(3):249-254.