Analysis of Personal Email Networks using Spectral Decomposition

We analyzed personal emails in forms of network data and proposed a new method for classifying spam and nonspam emails based on graph theoretic approaches. The proposed algorithm can distinguish between unsolicited commercial emails, so called spam and non-spam emails using only information in the email headers. We exploit the properties of social networks and spectral decomposition to implement our algorithm. In this paper, we mainly used the community structure in social network to classify non-spam and proposed a new method for edge partition of networks. We tested our method on one of author's mail box, and it classified 41% of all emails as spam or non-spam emails, with no error. And these results are obtained with only few subnetworks resulted from the proposed decomposition method. It requires no supervised training and soley based on properties of networks, not on the contents of emails.