Detecting Web Spams Using Evidence Theory
Detecting Web Spams Using Evidence Theory
复制标题
使用证据理论检测网络垃圾邮件
DOI：
10.1109/compsac.2018.10321
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
A. Namin
中科院分区：
文献类型：
--
作者：
Moitrayee Chatterjee;A. Namin
搜索引擎是网络上的主要工具。确定典型搜索引擎返回的结果的责任是一项艰巨的挑战，主要是因为存在Web垃圾邮件。新类型的网络垃圾邮件不时地不断出现，这使得决定结果的准确性变得非常具有挑战性。这个问题看起来像是一个存在不确定性的推理问题。本文提出了一种预测Web垃圾邮件的方法，其中主机的垃圾邮件性被表述为一个推理问题。该方法基于证据理论——一种基于邓普斯特-谢弗理论（DST）的数学预测模型。我们的Web垃圾邮件处理方法的主要优点是DST能够处理不确定性。当一个新的垃圾邮件被引入系统时，系统缺乏合理的先验知识。这就是DST在没有任何事先信息的情况下提供更可靠的解决方案来检测垃圾邮件的地方。本文对所提出的方法进行了详细的统计评估，其中检测Web垃圾邮件的准确率为99.27%。
Search engines are the major instruments on the Web. The determination of the liability of the results returned by a typical search engine is a daunting challenge mainly due to the presence of Web spams. New types of Web spams are continuously introduced every now and then, which makes it drastically challenging to decide about the accuracy of the results. The problem looks like a reasoning problem in the presence of uncertainty. This paper presents a methodology for predicting Web spam where the spamicity of hosts is formulated as a reasoning problem. The approach is based on evidence theory, a mathematical prediction model based on Dempster-Shafer Theory (DST). The key benefit of our approach for Web spam is DST's ability to deal with the uncertainty. When a new spam is introduced in the system, the system lacks a reasonable prior knowledge. This is where DST provides more liable solution to detect spams without any prior information. The paper presents detailed statistical evaluations of the proposed approach where an accuracy of 99.27% in detecting Web spams is reported.