[Spambayes] Ham:Spam ratio

[Russ Foster]

I have the spam problem (large imbalance of spam:ham).

It's probably not the most elegant solution, but I just manually move some
of my 'ham' (from the inbox, even though it was classified properly as
ham) into the 'unsure' folder.

Then highlight these good messages and click "Recover from Spam".

The reason you get so much unclassified is you don't have enough trained 
ham. If you keep the ratio in check (I would say anywhere between 1:1 and 
1:2 would suffice) you will start to see much better results.

-r

-- 
russ_foster at comcast.net


On Thu, 19 Feb 2004 dickk at paragonconstructioninc.com wrote:

> I've seen a lot of posts regarding this ratio that indicate 1:1 or 1:2 is an
> appropriate ratio.  My ratio is currently 446:5554 or about 1:121.
> 
> My real email statistics are about 98% spam, 2% ham.  When I started using
> SpamBayes two months ago, I didn't do any training, but rather started
> training on all new email.  Now about 60% of my mail goes to Junk and 39%
> goes to Junk Suspects.  Of the 39% unclassified, maybe 1% is actually ham.
> I'm not particularly unhappy with the way that it's working, I just don't
> know if I'm using it properly.
> 
> My questions are:  Should I expect that 39% of my mail is unclassified, or
> should it be less (or more)?  If I retrain to get a ratio of 1:2 or better,
> will that decrease the amount of unclassified mail?  If I retrain, how often
> should I retrain to keep the ratio proper?
> 
> Thanks
> Dick Kusleika
> Paragon Construction, Inc.