why is this not spam?

[David Relson]

On Wed, 4 Aug 2004 18:28:45 -0300
Trevor Smith wrote:

> On August 4, 2004 6:02 pm, David Relson wrote:
> > Bogofilter's default parameters were determined using the bogotune
> > program and a corpus of several hundred thousand messages from
> > several sources (personal email collections, 80-100 person
> > businesses, etc).  To
> 
> Right. So there is a default spam_cutoff value. But how high is it?

It's 0.99 :-)  Use "bogofilter -Q" to display all the parameters.  The
configuration file, /etc/bogofilter.cf, shows all the configurable
options.  Bogofilter's default values are in lines starting "##".

> > lower).  The effect of this is that ham messages are unlikely to be
> > scored as spam and that high scoring ("spammish") messages will
> > score as non-spam.  This "lets through" more spam (undesirable), but
> > results in fewer false positives (desirable).
> 
> Perfectly sound behaviour, especially "out of the box" when it has the
> 
> potential to do the most mischief. I would have built it no
> differently. Spam getting through is minorly annoying; losing 'good'
> emails is potentially quite harmful.

Exactly!

> > P.S.  When you disagree with bogofilter's classification
> > ("yes"/"no") of a message, use it to further train bogofilter.  That
> > will help bogofilter do better in the future.
> 
> Of course! Naturally I did this and bogofilter gave the spam a higher 
> spamicity score and caught it the next time it looked at it. :-)

That's the way it's 'sposed to work.  'Tis likely that bogofilter's
mantra should be "train, train, train".

Regards,

David