Bogofilter accuracy plummets starting around March 10, 2010

David Relson relson at osagesoftware.com
Sat Apr 10 00:30:42 CEST 2010


On Thu, 08 Apr 2010 13:11:12 +0400
Dmitry wrote:

> Jonathan Kamens wrote:
> > I also fed my entire old ham and spam corpuses through spamitarium
> > and then wiped out my word list and recreated it from scratch using
> > the new corpuses.
> > 
> >  
> > 
> > In the day since I made these changes, I've gone from 79% accuracy
> > to <http://stuff.mit.edu/~jik/#spam> >99% accuracy, so either all
> > the spam of the type that that was confusing bogofilter has
> > suddenly stopped (unlikely!) , or these changes were quite
> > successful.
> 
> Dear bogofilter maintainers,
> 
> May I ask again to make a config option "do not process invisible 
> headers"? It is so obvious that ommiting invisible headers improves 
> bogofilter accuracy in spite of what theory says. Why do we need
> another tool like spamitarium just to remove additional work instead
> of not doing that work at all?
> 
> -- 
> Dmitry

Hello Dmitry,

"Invisible headers" is not a term I recognize.  If you wish to have
particular headers ignored, I suggest you let grep do the work, i.e.
pipe your message through an appropriate "egrep -v "^(this|or|that):"
command.

HTH,

David



More information about the Bogofilter mailing list