[Spambayes] How Spam Bayes determines no Of Significant Words
tameyer at ihug.co.nz
Tue Feb 8 22:44:40 CET 2005
> How Spam Bayes determines no Of Significant Words In perticular Mail?
In addition to what Jesse said: once SpamBayes has a set of all tokens in a
message (and the individual scores for each token), all tokens within a
certain range (by default 0.4 to 0.6) are discarded, and the remainder are
sorted in order of their distance from 0.5. Up to 150 of the most
significant tokens (those furthers from 0.5) are used as the tokens to
generate the message's overall score.
Please always include the list (spambayes at python.org) in your replies
(reply-all), and please don't send me personal mail about SpamBayes.
http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this.
More information about the Spambayes