Mail.app’s Junk Filter is not like the others

I’ve blogged two excellent descriptions of the way this filter works in
The post describes the differences between Bayesian and LSA and a whole lot more. It’s over two years old, but a good read and packed full of links to other resources on spam.
[via Paul's Time Sink.]
Similar Posts:
- How Bayesian spam filtering works
- How Apple Mail’s Junk Filter works
- Image spam: Spam gets more canny
- Spamfire: Extra spam protection for Apple Mail
- Mail.app and SpamAssassin in spam-catching harmony
Tags: Apple Mail, Bayesian, bayesian filtering, junk filter, latent semantic analysis, lsa, mail.app, spam

February 16th, 2006 at 2:07 pm
[...] ‘Mail.app’s Junk Filter is not like the others’ contains a number of links to explanations of LSA and how it differs from Bayesian filtering. [...]
July 29th, 2006 at 8:35 am
It’s a bit too latent in my opinion. I have several types of spam that keep coming back again and again a few days after I’ve tagged them as junk even though they still look the same.
I’d love to find an easy way to set up SpamAssassin on the Mac (I’m using MailServe, so it’s running as my mailserver as well), that’s thusfar pretty much the only thing I’ve found capable of keeping 99.9% of the spam out.