期刊名称：IAENG International Journal of Computer Science
印刷版ISSN：1819-656X
电子版ISSN：1819-9224
出版年度：2020
卷号：47
期号：2
语种：English
出版社：IAENG - International Association of Engineers
摘要：In our everyday life, we may use email for personal and professional matters. Yet, email benefits have been bedeviled with the remarkable use of annoying, harmful, and fraudulent messages that commonly referred to as spam emails. Several antispam campaigns hover around machine learning and data mining techniques were devised in literature. An intelligent data mining approach referred to as Associative Classification (AC) presents itself as a possible method that might efficiently identify spam emails. In this study, an improved Spam Classification based on the Association Classification algorithm (SCAC) is proposed. In addition to the robust rule generation procedure, the improved model creation process, and the enhanced prediction mechanism, the SCAC algorithm is able to derive a new class value that doesn't exist in the original dataset that is the “Uncertain” class value. Hence, the SCAC algorithm doesn't introduce several contributions in the field of AC only but also it has contributed to the spam detection domain. These contributions have mutually reinforced the superb classification abilities of the SCAC algorithm when compared to several other intelligent techniques.
关键词：Association;Classification;Spam;e-mail;Multi- Class
