期刊名称：International Journal of Computer Science and Communication Networks
电子版ISSN：2249-5789
出版年度：2011
卷号：1
期号：3
页码：218-221
出版社：Technopark Publications
摘要：Now a Day’s, Email is one of the most prevalent personal and business communication tool, but it exhibits some significant drawbacks. One of the drawback of this is the portion of e-mail is that spam, has increased dramatically in the past few years. A recent study showed that 52 percent of e-mail users say spam has made them less trusting of e-mail, and 25 percent say that the volume of spam has reduced their e-mail use. This crisis has prompted proposals for a broad spectrum of potential solutions, ranging from more efficient antispam software tools to antispam laws at both the federal and state levels. But Still there is a necessity, to overcome this, in this paper We propose a novel approach that combines unsupervised clustering, social network analysis, semi supervised feature induction, and supervised classification to model user priorities among incoming email messages. This article presents the first study on PEP with a fully personalized methodology, where only each user’s personal email data. Finally results show that this method somehow better compared to other methods
关键词：WWW; Email; Containment; social network analysis
