Re: using libmilter, milter-spamc and spamassasin

From: Scot L. Harris (webid_at_cfl.rr.com)
Date: 05/29/04

  • Next message: Kevin F. Berrien: "Firewall - Very limited Access - suggestions" 
    To: For users of Fedora Core releases <fedora-list@redhat.com>
Date: Sat, 29 May 2004 15:51:21 -0400

    On Sat, 2004-05-29 at 15:03, Hannes Mayer wrote:

    >
    > Scot, so the bayesian filter doesn't learn automatically ?
    > I mean, one needs to train it once again with the filtered spam ?
    > Any details you can share about this are greatly appreciated!
    >
    > Thank you,
    > Hannes.

    There is an auto learn mode which does part of the job. From the stuff
    I have read and my experience, it is a good idea to run identified spam
    as well as ham messages through the sa-learn program to reinforce what
    it learns automatically. Also you will need to teach as spam those spam
    messages that get through.

    Also the bayesian filtering does not actually start until the system has
    learned from several hundred messages. And by feeding it a good sized
    sample of ham messages as well as identified spam messages you will
    reinforce what you believe is spam and ham. It seems to refine the
    identification process very well.

    I dump identified spam to a holding folder and unflagged spam to
    separate folder. Then once a week or so I run sa-learn against those
    folders and against my inbox which has all ham messages.

    Been doing this for awhile. Currently I get a handful of spam each week
    that gets through if that many. Have not had any false positives in a
    very long time.

    According to the docs feeding it steady diet of ham and spam will keep
    spamassassin happy and keep up with new tricks that the spammers try.

      

    -- 
Scot L. Harris <webid@cfl.rr.com>
-- 
fedora-list mailing list
fedora-list@redhat.com
To unsubscribe: http://www.redhat.com/mailman/listinfo/fedora-list
  • Next message: Kevin F. Berrien: "Firewall - Very limited Access - suggestions"

    Relevant Pages

    • Re: using libmilter, milter-spamc and spamassasin
      ... > I have read and my experience, it is a good idea to run identified spam ... > as well as ham messages through the sa-learn program to reinforce what ... Also you will need to teach as spam those spam ... > separate folder. ...
      (Fedora)
    • Re: Non-interactive changes to a message
      ... ham messages get classified as spam. ... > I'm using spamprobe and am very happy with it. ... Prev by Date: ...
      (comp.mail.mutt)
    • Re: Non-interactive changes to a message
      ... ham messages get classified as spam. ... Andre Berger wrote: ... > I'm using spamprobe and am very happy with it. ...
      (comp.mail.mutt)
    • Re: SpamAssassin (3.0.2) unbreakable?
      ... Your earlier post made me curious, so I installed SpamAssassin ... It was working -- no false positives, but some spam ... and ham messages. ... Spam has gotten a spam score of 6-15. ...
      (comp.os.linux.misc)
    • Re: Mark an email as junk because of the TYPE of email, not the domai.
      ... > The program I was referring to is I Hate Spam which I was using the ... have no statistics yet on which to exercise against new e-mails. ... IHateSpam also incorporates Bayesian filtering. ... IHateSpam did a better job than the new Bayesian filter incorporated ...
      (microsoft.public.outlook.general)