复杂网络性质探讨及在垃圾邮件过滤中的运用

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z6): 145-148.

复杂网络性质探讨及在垃圾邮件过滤中的运用

李渊,廖闻剑,彭艳兵,程光

武汉邮电科学研究院武汉430074;武汉邮电科学研究院武汉430074;武汉邮电科学研究院武汉430074;东南大学江苏省网络重点实验室南京210096

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家973计划(2009CB320505),江苏省科技支撑计划(BE2011173)资助

Discussion of the Characters of Social Network and the Application of Spam Filtering

LI Yuan,LIAO Wen-jian,PENG Yan-bing and CHENG Guang

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 基于描述社会网络中幂律分布和小世界效应的网络理论,社会计算能够定量分析社会行为的规律。首先通过幂律分布特征从统计意义上区分了网络中两类度数有差异的节点,这样的方法可以用于垃圾邮件过滤。考虑小世界效应后得到网络平均距离变化缓慢的动态性质,该性质指出了一种平均距离相对固定的网络模型构造思路。最后以邮件数据为实验对象,验证了节点分类的方法对垃圾邮件过滤的有效性。

关键词: 社会网络,幂律分布,小世界效应,垃圾邮件过滤

Abstract: Based on the network theory’s capability to describe both the power-law distribution and the small-world effect in the social networks,the societal computing can measure the complex behavior in the society．Firstly the statistical method is proposed to distinguish two types of nodes with different active degrees through the character of the power-law distribution,which can be deployed as spam filter．Considering the small-world effect,the average distance between any two nodes changed lightly while the number of nodes varied significantly．The characters of different active nodes were validated in the spam filtering procedure from the original electrical mail records at last.

Key words: Social networks,Power-law distribution,Small-world effect,Spam filter

李渊,廖闻剑,彭艳兵,程光. 复杂网络性质探讨及在垃圾邮件过滤中的运用[J]. 计算机科学, 2013, 40(Z6): 145-148. https://doi.org/

LI Yuan,LIAO Wen-jian,PENG Yan-bing and CHENG Guang. Discussion of the Characters of Social Network and the Application of Spam Filtering[J]. Computer Science, 2013, 40(Z6): 145-148. https://doi.org/

参考文献

[1] Kleinberg J．The small-world phenomenon:An algorithmic perspective[C]∥ACM Symposium on Theory of Computing．2000,32
[2] Newman M E J．Models of the small world[J]．Journal of Statistical Physics,2000,101:819-841
[3] Watts D J．The "New" Science of Networks[J]．Annual Review of sociology,2004,30:243-270
[4] Watts D J,Strogatz S H．Collective dynamics of ''small-world''networks[J]．Nature,1998,393:440-442
[5] Newman M E J,Strogatz S H,Watts D J．Random graphs with arbitrary degree distributions and their applications[J]．Physical Review E,2001,64
[6] Clauset A,Shalizi C R,Newman M E J．Power-law distributions in empirical data[J]．SIAM Review,2009,51:661-703
[7] Newman M E J．Power laws,Pareto distributions and Zipf''s law[J].Contemporary Physics,2005,46:323-351
[8] Iversen G R,Gergen M．统计学[M]．吴喜之,等译．北京:高等教育出版社,2002:235-237
[9] Arbesman S,Kleinberg J,Strogatz S．Superlinear Scaling for Innovation in Cities[J]．Physical Review E,2009,79
[10] Cohen R,Havlin S．Scale-Free Networks Are Ultrasmall[J]．Physical Review Letters,2009,90
[11] Easley D,Kleinberg J．Networks,Crowds,and Markets:Reaso-ning About a Highly Connected World[M]．Cambridge University Press,2010:63
[12] Symantec Corp．Symantec Announces August 2011 SymantecIntelligence Report[EB/OL]．http://www.symantec.com/about/news/release/article.jsp?prid=20110823_01,2011-08-23
[13] 张铭峰,李云春,李巍.垃圾邮件过滤的贝叶斯方法综述[J].计算机应用研究,2005(8):14-19
[14] 王斌,潘文锋．基于内容的垃圾邮件过滤技术综述[J].中文信息学报,2005(8):1-10
[15] Zhao Y,et al.BotGraph:Large Scale Spamming Botnet Detection[C]∥Proceedings of the 6th USENIX Symposium on Networked Systems Design and Implementation(USENIX,Berkeley,CA)．2009:321-334

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed