-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
On Mar 14, 2008, at 9:51 AM, Tim Palmer wrote:
> Robert Fitzpatrick wrote:
>> On Thu, 2008-03-13 at 23:28 -0400, Tim Palmer
wrote:
>>
>>> 0.000 0 244301 0
non-token data: nspam
>>> 0.000 0 51666 0
non-token data: nham
>>>
>>
>> Are you by any chance experiencing false positives
due to bayes
>> scoring?
>> I had that problem when my counts were so lopsided
> Hard to say. I'm one step removed from the users on
this server. For
> my
> account on a domain on this, mailing lists do get FP
fairly often,
> but I
> don't mind (<shameless plug for Maia> thanks to
the ease of
> recovery!).
> It is, of course, standard user behavior to not confirm
much, and to
> mostly confirm FPs, without really clearing out
ham/spam caches. I
> fully
> expect low confirmation rates, and a basis in bayes
towards nspam
Heck, even *I* get lazy in my confirmations... lol. What I
like most
is the digest feature... when a few spam slip through
(anyone else get
a surge last night?) I look for the most recent digest, mark
the ones
it misclassified, and then hit the "confirm all"
link at the bottom.
That usually gets the bayes back in line.
David Morton
Maia Mailguard http://www.maiamailguard
.com
mortonda dgrmm.net
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (Darwin)
iD8DBQFH2qclUy30ODPkzl0RAunIAJkB38R0acSs5E8Zi04RoJzfRsXXUwCd
Gjcj
EHaJ0S9CgX0cM1qk2mqjXBY=
=zst/
-----END PGP SIGNATURE-----
_______________________________________________
Maia-users mailing list
Maia-usersrenaissoft.com
http://www.renaissoft.com/mailman/listinfo/maia-users
|
