本站原创
文章编号:10019081(2013)07186105
doi:10.11772/j.issn.10019081.201
针对目前垃圾邮件过滤技术仅依赖单一邮件特征实施邮件分类、对邮件特征变化的适应性较差等局限，提出一种基于用户反馈的混合型垃圾邮件过滤方法。以用户社会网络关系为基础，借助用户反馈机制分别实现对基于内容与基于身份标识的邮件分类知识的动态更新；在此基础上采用贝叶斯模型，实现邮件的内容特征与发件人身份标识特征在邮件分类中的有机结合。实验结果表明，与传统的过滤方法比较，所提方法在邮件特征动态变化的环境下能够获得更好的邮件分类效果，邮件分类的总体召回率、查准率、精确率均能达到90%以上。所提方法能够在保证邮件分类性能的同时，有效提高邮件分类对邮件特征变化的适应性，是已有垃圾邮件过滤技术的重要补充。
关键词：垃圾邮件；基于内容的邮件过滤；基于身份标识的邮件过滤；邮件分类；用户反馈；贝叶斯模型
:A
英文标题
Hybrid spam filtering method based on users feedback
英文作者名
HUANG G
英文地址(
1. Computer College, Shenzhen Institute of Information Technology, Shenzhen Guangdong 518172, China;
2. College of Information Technical Science, Nankai University, Tianjin 300071, China英文摘要)
Abstract：
Several limitations exist in the current spam filtering methods, such as they usually rely on only one type of Email characteristic to realize the Email classification, and he poor adaptability to the dynamic changes of Email characteristics. Concerning these limitations, a hybrid spam filtering method based on users feedback was proposed. Based on the Social Network (SN) relationship among users, the dynamic update of the knowledge for Email classification was achieved with the help of the users feedback scheme. Furthermore, the Bayesian model was introduced to integrate the contentbased and the identitybased characteristics of Email in the classification. The simulation results show that the proposed method outperforms the traditional method in terms of Email classification, when the Email characteristics change dynamically. The overall recall, precision and accuracy ratios of the method can achieve 90% and above. While guaranteeing the performance of Emailclassification, the proposed method can improve the adaptability of classification to the changes of Email characteristics effectively. Therefore, the proposed method can act as a useful complement to the current spam filtering methods.
Several limitations exist in the current spam filtering methods, such as they usually rely on only one type of Email characteristic to realize the Email classification, and he poor adaptability to the dynamic changes of Email characteristics. Aiming at such limitations, a hybrid spam filtering method based on users’ feedback was proposed. Based on the Social Network (SN) relationships among users, the dynamic update of the knowledge for Email classification was achieved with the help of the user’s feedback scheme. Furthermore, the Bayesian model was introduced to integrate the contentbased and the identitybased characteristics of Email in the classification. The simulation results show that the proposed method outperforms the traditional method in terms of the performance of Email classification, when the Email characteristics change dynamically. The overall recall, precision and accuracy ratios of the method can achieve 90% and above. While guaranteeing the performance of Email classification, the proposed method can improve the adaptability of classification to the changes of Email characteristics effectively. Therefore, the proposed method can act as a useful complement to the current spam filtering methods.
doi:10.11772/j.issn.1001908
1.2013.07.1861
摘 要：
针对目前垃圾邮件过滤技术仅依赖单一邮件特征实施邮件分类、对邮件特征变化的适应性较差等局限，提出一种基于用户反馈的混合型垃圾邮件过滤方法。以用户社会网络关系为基础，借助用户反馈机制分别实现对基于内容与基于身份标识的邮件分类知识的动态更新；在此基础上采用贝叶斯模型，实现邮件的内容特征与发件人身份标识特征在邮件分类中的有机结合。实验结果表明，与传统的过滤方法比较，所提方法在邮件特征动态变化的环境下能够获得更好的邮件分类效果，邮件分类的总体召回率、查准率、精确率均能达到90%以上。所提方法能够在保证邮件分类性能的同时，有效提高邮件分类对邮件特征变化的适应性，是已有垃圾邮件过滤技术的重要补充。关键词：垃圾邮件；基于内容的邮件过滤；基于身份标识的邮件过滤；邮件分类；用户反馈；贝叶斯模型
:A
英文标题
Hybrid spam filtering method based on users feedback
英文作者名
HUANG G
源于：如何写论文www.udooo.com
uowei1*, XU Yuwei2英文地址(
1. Computer College, Shenzhen Institute of Information Technology, Shenzhen Guangdong 518172, China;
2. College of Information Technical Science, Nankai University, Tianjin 300071, China英文摘要)
Abstract：
Several limitations exist in the current spam filtering methods, such as they usually rely on only one type of Email characteristic to realize the Email classification, and he poor adaptability to the dynamic changes of Email characteristics. Concerning these limitations, a hybrid spam filtering method based on users feedback was proposed. Based on the Social Network (SN) relationship among users, the dynamic update of the knowledge for Email classification was achieved with the help of the users feedback scheme. Furthermore, the Bayesian model was introduced to integrate the contentbased and the identitybased characteristics of Email in the classification. The simulation results show that the proposed method outperforms the traditional method in terms of Email classification, when the Email characteristics change dynamically. The overall recall, precision and accuracy ratios of the method can achieve 90% and above. While guaranteeing the performance of Emailclassification, the proposed method can improve the adaptability of classification to the changes of Email characteristics effectively. Therefore, the proposed method can act as a useful complement to the current spam filtering methods.
Several limitations exist in the current spam filtering methods, such as they usually rely on only one type of Email characteristic to realize the Email classification, and he poor adaptability to the dynamic changes of Email characteristics. Aiming at such limitations, a hybrid spam filtering method based on users’ feedback was proposed. Based on the Social Network (SN) relationships among users, the dynamic update of the knowledge for Email classification was achieved with the help of the user’s feedback scheme. Furthermore, the Bayesian model was introduced to integrate the contentbased and the identitybased characteristics of Email in the classification. The simulation results show that the proposed method outperforms the traditional method in terms of the performance of Email classification, when the Email characteristics change dynamically. The overall recall, precision and accuracy ratios of the method can achieve 90% and above. While guaranteeing the performance of Email classification, the proposed method can improve the adaptability of classification to the changes of Email characteristics effectively. Therefore, the proposed method can act as a useful complement to the current spam filtering methods.