case folding [was: tuning ]

David Relson relson at osagesoftware.com
Tue May 6 20:01:49 CEST 2003


At 01:37 PM 5/6/03, Joerg Over wrote:

>Hi there,
>
>Am 12:01 06.05.2003 -0400 teilte David Relson mir folgendes mit:
>->score.  Generally, the more information bogofilter has to work
>with, the
>->better it will do its job.
>
>In that line of thought: Why is case mangled in the database?
>I'd believe that there _would_ be a difference and maybe greater
>accuracy.
>I'd think there's a difference between "money" and "MONEY" when
>it comes to spam.
>Since I'm sure this has been discussed before, a tiny pointer to
>the discussion would be sufficient for me, I tried, but failed to
>find that subject in the archives.
>
>Thx in advance, jo

Case folding saves on database size.  Without it, you might have "money", 
"Money", "MONEY", "monEy", ...






More information about the Bogofilter mailing list