Re: [Ifile-discuss] Improving classification of spams

[Clemens Fischer]

Booker Bense <address@hidden>:

> - So far, I've had very good luck with the spam/non-spam issue,
> however I have hybrid system where I index everything, but only
> use ifile as a last resort. (i.e. I have a bunch of prefilters
> based on the sender/headers if none of those match see what ifile
> suggests. ) Every message is indexed by ifile after it gets
> filtered.

i discontinued doing this thinking that i'd prevent ifile to see some
of the spam and therefore not training it correctly.

> - What I've done is distinguish between "ispam" and "spam". ispam
> is basically anything that isn't plain ascii and spam is for
> ascii readable spam.

it would be better to use metamail to make every message usable
directly for ifile, but i never found a version that leaves non-MIME
alone, so i had to ditch that approach.  as it turns out, the mere
existence of MIME tags in messages is often enough to make ifile
correctly classify it as spam.  but this is only good if ifile is
used to distinguish only ham from spam!

> - Also, I throw away the .idata file and reindex things every
> couple of weeks. Not sure if this has any effect or not.

i think this doesn't do much good.  how dod you get the feeling that
doing this is useful?

> P.S. I have a Ruby module for using ifile w/the rmail package
> if anybody is interested.

if you are talking emacs here, i'd like to see a copy :)

  clemens