A novel approach for clustering e-mail users using pattern matching

Emails have been considered as a useful resource for research in fields like link analysis, social network analysis and textual analysis, Email mining is a process of discovering useful patterns from emails. Clustering techniques can be applied over email data to create groups of similar emails. An email can be represented as an Object consisting of several attributes like sender email-id, receiver email-id Subject, message, sending-time, and attachments etc. clustering is used to discover email groups. Generally the most of the attributes in emails are text type, so text similarity techniques are used for measuring the similarity between pair of email objects. Clustering the emails and the user depend on the information they have exchanged and graphically representing Cluster. The Enron email dataset is a touchstone for such research.