Some directions in mining the Enron mail dataset, which can be found there : https://www.cs.cmu.edu/~./enron/enron_mail_20150507.tgz (423Mb, tarred and gzipped)
1 / loadenron.py file provide the Python source to load and clean, at a first glance, the enron mail data
2 / enronanalysis.R file provide the R source for topic and sentiment analysis