Spam Filter ISP Support Forum

  New Posts New Posts RSS Feed - Why haven't I seen anything blocked by Bayesian Filter?
  FAQ FAQ  Forum Search   Register Register  Login Login

Why haven't I seen anything blocked by Bayesian Filter?

 Post Reply Post Reply
Author
benny View Drop Down
Guest Group
Guest Group
Post Options Post Options   Thanks (0) Thanks(0)   Quote benny Quote  Post ReplyReply Direct Link To This Post Topic: Why haven't I seen anything blocked by Bayesian Filter?
    Posted: 14 December 2004 at 11:17am

corpus.ini

[Messages]
Spam=5566
Good=46480

 

Back to Top
LogSat View Drop Down
Admin Group
Admin Group
Avatar

Joined: 25 January 2005
Location: United States
Status: Offline
Points: 4105
Post Options Post Options   Thanks (0) Thanks(0)   Quote LogSat Quote  Post ReplyReply Direct Link To This Post Posted: 14 December 2004 at 6:12pm
Benny,

Please see http://www.logsat.com/spamfilter/forums/showmessage.asp?messageID=4620 for an explanation.

Roberto F. LogSat Software
Back to Top
ktrunkett View Drop Down
Newbie
Newbie


Joined: 07 February 2005
Status: Offline
Points: 30
Post Options Post Options   Thanks (0) Thanks(0)   Quote ktrunkett Quote  Post ReplyReply Direct Link To This Post Posted: 15 December 2004 at 9:33pm

my corpus is:

[Messages]
Spam=31412
Good=28248

I've only seen 4 emails get caught by the Bayesian filter, and they were all false positives. 

Back to Top
LogSat View Drop Down
Admin Group
Admin Group
Avatar

Joined: 25 January 2005
Location: United States
Status: Offline
Points: 4105
Post Options Post Options   Thanks (0) Thanks(0)   Quote LogSat Quote  Post ReplyReply Direct Link To This Post Posted: 17 December 2004 at 12:02am
Kriss, In average spam messages are 5-20 times more that good messages. Our own corpus.ini file looks like this:

[Messages] Spam=9105146 Good=559984

We receive 20x more spam than good emails. Still, under these conditions, during the past 3 days we blocked 100,000 emails using MAPS filter, 90,000 using blacklisted countries, and only 1,000 using Bayesian filtering.

Being in yours and Benny's case spam and clean counts so close, it may be hard for the statistical filter to accurately determine what is spam and what is not. If you wish we can try emailing you our own corpus database to see if it makes a difference.

Roberto F. LogSat Software
Back to Top
 Post Reply Post Reply
  Share Topic   

Forum Jump Forum Permissions View Drop Down



This page was generated in 0.199 seconds.