yep, thats correct you have to have a set of spam and ham emails then thats where your engine will base, and you also need to update this from time to time as the spam keeps finding way ... you might want also to use lucene as your search engine
-buics On 5/18/07, Stefano Bagnara <[EMAIL PROTECTED]> wrote:
nur hazwani ha scritto: > Hi All, > I'm wany, > > Downloaded James 2.3.1, platform-windows-NT, Java 2 SDK 1.4,MySQL > version 1.4 > i can run my James, my James can work properly,but i want to spam email > using bayesian analysis in JAMES, but it's cannot do it! > i also can connect with MySQL database and i create mail database. in > mail database, i have > bayesiananalysis_ham,bayesiananalysis_messagecounts,bayesiananalysis_spam, > inbox,spool,deadletter tables in mail database. > > i also have uncomment that related with Bayesian Analysis and bayesian > Analysis Feeder in config.xml. i try to send spam email, but they cannot > filter spam into database. > > i need help to filter spam email using bayesian analysis...........plz > help me..........urgent! > > thanks a lot.......... http://wiki.apache.org/james/Bayesian_Analysis Btw, you have to train the filter: bayesian needs training (or you need an existing spam/ham corpus). Stefano --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
-- "Programs must be written for people to read, and only incidentally for machines to execute." - Abelson & Sussman, SICP, preface to the first edition --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
