You need to train SpamBayes what you regard as spam and what you don't. Every time you train on an incorrectly classified message, the classification of messages that arrive later should improve. I'd recommend just using it; don't try testing it with messages that you construct, because they'll almost certainly differ in important ways from actual spam. For instance, if you send messages to yourself from some address and tell SpamBayes that those messages are spam, you'll increase the odds that future messages from that address will be classified as spam, which you might not want.
 


From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of frederic Courcelles
Sent: Wednesday, March 15, 2006 9:29 AM
To: [email protected]
Subject: [Spambayes] spambayes

i don't understand how they know if my email it's a spam or not i try to send 3 email and all say unsure but i put in subject first test second : penis and third time :test penis please let me know thanks
_______________________________________________
[email protected]
http://mail.python.org/mailman/listinfo/spambayes
Check the FAQ before asking: http://spambayes.sf.net/faq.html

Reply via email to