"Eyvonne Sharp" <[EMAIL PROTECTED]> writes: > I haven't been able to find any information in the docs on what messages > are auto_learned and why. Users that have received over thousands of > emails and have had hundreds of messages classified as spam will only > have a bayes_msgcount of 94. Does that mean that auto_learn has only > 'read' 94 email messages? If this is the case, it isn't very helpful.
You can tweak the spam/ham auto-learn thresholds. Look at bayes_auto_learn_threshold_nonspam and bayes_auto_learn_threshold_spam. I wouldn't suggest changing them too much. To achieve good accuracy, auto-learning only learns from messages that are particularly spammy or particularly non-spammy. Daniel ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
