E-mail authorship attribution using customized associative classification

摘要: E-mail communication is often abused for conducting social engineering attacks including spamming, phishing, identity theft and distributing malware. This largely attributed to the problem of anonymity inherent in standard electronic mail protocol. In literature, authorship attribution studied as a text categorization where writing styles individuals are modeled based on their previously written sample documents. The developed model employed identify most plausible writer text. Unfortunately, existing studies focus solely improving predictive accuracy not value evidence collected. this study, we propose customized associative classification technique, popular data mining method, address problem. Our approach models unique style features person, measures associativity these produces an intuitive classifier. results obtained by experiments real dataset reveal that presented method very effective.