I am trying to find out how exactly bayesian filtering works but I am not clear on it.
My question is how bayesian filtering actualy works i-e it collects the words from whole message (header, body & subject) or just body & subject or just from body.
In my scenario users forward me those spam messages (ham) which are incorrectly marked as spam and those ham messages (spam) which are actualy spam.
My problem in this way is that orignal messages are now modified and extra headers and signatures are also added with them and I am curious that this will train the filter in wrong manner.
Protecting your Linux box
3 posts • Page 1 of 1
Who is online
Users browsing this forum: No registered users and 1 guest