Suspicious E-mail detection via decision tree: A data mining approach

Abstract

Data mining is the quest for knowledge in databases to uncover previously unimagined relationships in the data. This paper proposes to apply Decision tree in Suspected e-mail detection (e-mails about criminal activities). Deception theory suggests that deceptive writing is characterized by reduced frequency of first person pronouns and exclusive words and elevated frequency of negative emotion words and action verbs. We applied this model of deception to the set of e-mail dataset, then applied ID3 algorithm to generate the decision tree. The decision tree that is generated is used to test the e-mail as suspicious or not. In particular, we are interested in detecting fraudulent and possibly criminal activities from such data.