Mailing list analysis tool for community pattern detection

We developed an IMAP server-based mailing list parser to analyze community structure and derive hypergraphs on communication patterns. Some questions we asked:

• what is the Dunbar’s number for this list?
• Is there a correlation between the number of authors and the length of a thread?
• What is the churn rate of this network?
• Which factors make a thread popular, and can text mining help us detect them?