To use automatic learning, set the bayes_auto_learn flag to 1. This can be
configured site-wide in the /etc/mail/spamassassin/local.cf file, and can be
overridden in a user's ~/.spamassassin/user_prefs file. Two other configuration
flags also affect auto-learning, and are the thresholds for learning ham and
spam. These values are in the same units as SpamAssassin's score for each
email.
bayes_auto_learn 1
bayes_auto_learn_threshold_nonspam 0.1
bayes_auto_learn_threshold_spam 12.0
________________________________
From: Gene Heskett [mailto:[EMAIL PROTECTED]
Sent: Mon 2/12/2007 1:33 PM
To: users@spamassassin.apache.org
Cc: Jim Maul; Jack Gostl; Anthony Peacock
Subject: Re: Bayes resolution gettin weaker
On Monday 12 February 2007 13:35, Jim Maul wrote:
>Jack Gostl wrote:
>> Well... I'm convinced. I turned off autolearn a week ago, and things
>> have never been smoother. Its a shame really, that's a nice feature,
>> but for some reason it waters down the Bayes resolution until its
>> almost useless.
>
>Most likely because the autolearn thresholds are too generous. The
>possibility to autolearn spam as ham and/or ham as spam is too great. I
>have been running with autolearn enabled, my thresholds set to:
>
>bayes_auto_learn_threshold_nonspam -0.1
>bayes_auto_learn_threshold_spam 12.0
>
Where are these rules located?
>without any problems for almost 3 years now. My bayes database has
>never been better. I think too many people have problems with it
>because of the defaults and instead of trying to figure out how to make
>it work better, they just turn it off and call it "broken".
>
>-Jim
>
>> ----- Original Message ----- From: "Jack Gostl" <[EMAIL PROTECTED]>
>> To: "Anthony Peacock" <[EMAIL PROTECTED]>; "SpamAssassin"
>> <users@spamassassin.apache.org>
>> Sent: Monday, February 05, 2007 7:06 AM
>> Subject: Re: Bayes resolution gettin weaker
>>
>>> ----- Original Message ----- From: "Anthony Peacock"
>>> <[EMAIL PROTECTED]>
>>> To: "SpamAssassin" <users@spamassassin.apache.org>
>>> Sent: Monday, February 05, 2007 3:56 AM
>>> Subject: Re: Bayes resolution gettin weaker
>>>
>>>> Hi,
>>>>
>>>> Jack Gostl wrote:
>>>>>>> I've been watching this for awhile, and there is now a pattern to
>>>>>>> what I'm seeing.
>>>>>>>
>>>>>>> I'm running a configuration with multiple users sharing a bayes
>>>>>>> files. This is an interim move to facilitate the spamassassin
>>>>>>> upgrades, and like many interim moves its been going on for a
>>>>>>> long time.
>>>>>>>
>>>>>>> When I first build the bayes files from my personal folders and
>>>>>>> my spam archives, things were great. 99.8% of the spam caught or
>>>>>>> better. Then, usually after a week or so, the number starts to
>>>>>>> drop. Right now, its down to 97%, in another day or two it will
>>>>>>> be down below 95%. With the amount of spam we receive, that is a
>>>>>>> lot of missed junk mail.
>>>>>>>
>>>>>>> So I blow away my bayes* files, rebuild, and I'm back up to darn
>>>>>>> near 100% caught. For about a week. Then the deterioration begins
>>>>>>> again.
>>>>>>>
>>>>>>> Has anyone else encountered this? Is this an artifact of too many
>>>>>>> users sharing a spam file?
>>>>>>>
>>>>>>> Also.... I retrain each night, feeding any missed spams plus any
>>>>>>> new hams received back through sa-learn. I can't see how that
>>>>>>> makes it worse, but who knows.
>>>>>>
>>>>>> Do you have autolearn enabled?
>>>>>
>>>>> Uh... yes? You are suggesting that I turn it off? I had always
>>>>> assumed that if the Bayes learned something as ham that it
>>>>> shouldn't, sa-learn was smart enough to undo it.
>>>>
>>>> Change the thresholds for auto learning. Mine are:
>>>>
>>>> bayes_auto_learn_threshold_nonspam -0.1
>>>> bayes_auto_learn_threshold_spam 12.0
>>>
>>> I'm willing to try. I made the change in my user_prefs and we'll see
>>> what the next week brings.
>>>
>>> Thanks
--
Cheers, Gene
"There are four boxes to be used in defense of liberty:
soap, ballot, jury, and ammo. Please use in that order."
-Ed Howdershelt (Author)
Yahoo.com and AOL/TW attorneys please note, additions to the above
message by Gene Heskett are:
Copyright 2007 by Maurice Eugene Heskett, all rights reserved.
