Had noticed in a recent thread on training problems that there appears to be a utility in the Outlook version of SpamBayes that allows you to examine the clues that spambayes used on a given message to decide how to classify it. I was wondering if there's a Unix command-line equivalent that I can use to check to see how a message is treated...
Spambayes has been working pretty great for me actually, I use a .procmail filter and it never misclassifies ham as spam, I only get spam misclassified as ham or unsure-- which is exactly how I want it. However, I have noticed some very short spam messages of late that seem to be resistant to training-- probably simply *because* they are so short there's not enough to go on, but I was curious as to how they are viewed in SpamBayes and a utility to let me know a little more-- a more "verbose" mode when training or running just the classifier with a verbose flag or something could be useful... Before I used spambayes I had a filter of my own design-- was tired of maintaining it though. It did allow me to add rules like "if the message is fewer than X English words, then it's likely SPAM." which would have weeded out most of this stuff that seems to be getting past SpamBayes... If anyone knows of any reporting aids that exist in the Unix version, I'd appreciate a "clue" to their whereabouts... -- Sync _______________________________________________ SpamBayes@python.org http://mail.python.org/mailman/listinfo/spambayes Info/Unsubscribe: http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
