On Wed, 16 Mar 2005, Alun wrote:
> Marc Sherman (msherman@???) said, in message
> <42383500.2050202@???>:
> >
> > Wouldn't an unmodified bayesian filter still account for that by
> > assigning a negative probability to the "Date: " token?
>
> Argh!
>
> You might be right, but I can't see the flaw in my reasoning. This is going
> to mess with my mind!
You're dealing with P(spam | date) and P(spam | no date) which are not
directly comparable (though reference to an A-Level probability textbook
should help).
Tony.
--
<fanf@???> <dot@???>
http://dotat.at/ ${sg{\N${sg{\
N\}{([^N]*)(.)(.)(.*)}{\$1\$3\$2\$1\$3\n\$2\$3\$4\$3\n\$3\$2\$4}}\
\N}{([^N]*)(.)(.)(.*)}{\$1\$3\$2\$1\$3\n\$2\$3\$4\$3\n\$3\$2\$4}}
