spam levels [was: Including html-tag contents ...]
Tony L. Svanstrom
tony at moon.pp.se
Tue May 13 20:44:39 CEST 2003
On Mon, 12 May 2003 the voices made David Relson write:
DR> I'm still not clear on your idea. It sounds like you want to change a
DR> percentage of the token scores to 0.0 or to 1.0.
DR> So "-u 1" would take the lowest 30% of the hammish tokens and change their
DR> scores to 0.0, i.e. "pure ham", and that "-u 4" would take the highest 20%
DR> and set them to 1.0???
Almost, instead of replacing any tokens these would be added with a
max/minimum score.
DR> Given a message of 100 words, suppose 50 were eliminated by MIN_DEV and of
DR> the remaining 50 words, 20 had hammish scores (less than 0.50) and 30 had
DR> spammish scores (above 0.50). What effect would values "-U1", "-U2", etc
DR> have??? (Note: since "-u" is in use and "-U" is not used, I'm using "-U"
DR> to designate the "Unsure" switch.)
The spammish/hammish tokens would be added on top of the existing ones, so
you'd end up with this many tokens.
100 words/tokens, 50 MIN_DEV-eliminated, 30 spammish and 20 hammish tokens
from the text used; resulting in this many spammish/hammish tokens to be used:
Spammish Hammish
-U1 30 40
-U2 30 30
-U3 30 20
-U4 40 20
-U5 50 20
--
.-------------------------------------------------------------------.
| Per scientiam ad libertatem! (Through knowledge towards freedom!) |
`-------------------------------------------------------------------´
<< ©1998-2003 tony at svanstrom.com >>
More information about the Bogofilter
mailing list