Hello Adam, Saturday, November 9, 2002, 9:01:24 PM, you wrote:
AB> Saturday, November 9, 2002, 8:52:35 PM, rick wrote: >> after 2 days it is working quite well. It uses probability instead of >> static filters. Works wonderful so far. AB> Are you just using it to filter spam? I was interested in replacing AB> all my bat rules with this, but I don't know how well it would work. AB> Given that my current filters get 90% of my spam anyway, I'm not sure AB> it's worth it. I have replaced all my bat rules and now have three rules. POPFile adds a line of text at end of header like this X-Text-Classification:personal I then have the three rules. One rule catches the personal, one catches the spam and one catches thebatlist. In two days I am very impressed. Remember you have to train it. You set it up and then when you get emails you classify them for POPfile. In doing this for one day I have achieved over 95%. Before I rebooted, I had processed 122 messages. POPFile recorded 99.22% accuracy. However, this accuracy started after the 100th email therefore 21 out of 22 were process correctly after just 1 day of use. What really impressed me with POPFile is that it correctly put my officemax.com (officemax.com emails are very similar in nature to spam) emails in my personal folder while stopping similar spam messages. It did this after training. I am very happy with it. -- Best regards, rick ________________________________________________ Current version is 1.61 | "Using TBUDL" information: http://www.silverstones.com/thebat/TBUDLInfo.html
