Re[3]: Bayesit
Hello Philip, Friday, January 23, 2004, 9:58:11 AM, you wrote: PS> However, at the moment, I'm only aware of one free filter plugin for PS> spam - bayesit - so this very nice feature of The Bat! goes unused as PS> yet. Hopefully you can now see why the plugin architecture is so PS> valuable, though. BayesFilter Download: http://www.lkcc.org:8500/download/bayesfilter.zip BayesIT Download: http://klirik.narod.ru/usefuls/bayesit.htm VampireX Download: http://vampirex.fabiangonzalez.cl/ -- Stuartmailto:[EMAIL PROTECTED] Using The Bat! v2.03 Beta/45 on Windows 98 4.10 Build A Current version is 2.02.3 CE | "Using TBUDL" information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit
Hi Philip, On Friday, January 23, 2004 at 3:58 PM, Philip wrote: > Friday, January 23, 2004, 10:58:14 AM, you wrote: T>> That's the same question I had. As I have SpamAssassin on the mail T>> server, most of my spam gets caught and filtered that way, but I was T>> hoping that this would catch the one or two that slip by every week. > If SpamAssassin on your mail server is preventing spam mails from > getting to your copy of The Bat!, then you should really disable it. Thanks for your response, but I think you must have misunderstood what I wrote. I'm not having any problems with SpamAssassin on the mail server. By "caught" I mean that SpamAssassin is doing exactly what it is supposed to do and works exactly how I've set it up - it evaluates all incoming mail for spam, adds the appropriate headers and forwards it to my mailbox where I then download all mail. I then use filters on TB to separate out the spam based on the header information. > Having two spam filters is not actually a good idea in most cases. If > one deletes a spam or otherwise stops it from being seen by the other > filter, then the other filter cannot evaluate it. Worse, if it if a > statistical filter - a bayesian one like bayesit - then that filter > will not learn about the spam's content and be able to update its > filtering. I have used two filters in the past with no problems at all. I used a SpamAssassin and popfile combination for almost a year. Popfile caught those that SpamAssassin scored low. When the plug-in became available, I switched to the BayesIt plug-in and Bayes Filter plug-in instead of popfile (one less program that's running). Neither has worked. I've read multiple posts both on this list and on the RitLabs Forum to know that I am not the only one having this problem with BayesIt. It works for some and not for others. I haven't heard much about Bayes Filter. > The only exception for this that I can think of is the way The Bat! > implements its plug-in architecture - which allows multiple filters, > all of which report a score. You can then choose to act on the lowest > (minimal) or highest (maximal) amongst the results, or to use an > average from all filters. (See the anti-spam plugin filters preference > page for details - it's not obvious at first!) > This multi-plugin capability means that The Bat! would decide what to > do after all filters have had a chance to look at the mail and report > their findings. It also means that marking mail as junk would cause it > to be analysed by multiple filters, improving the detection by all > filters in the future. I'm aware of how the plug-ins are supposed to work and how e-mails can be scored by multiple plug-ins, scores can be averaged, etc. Unfortunately, none of the current anti-spam plugins work as effectively as SpamAssassin does on my server. That's my experience. YMMV > However, at the moment, I'm only aware of one free filter plugin for > spam - bayesit - so this very nice feature of The Bat! goes unused as > yet. Hopefully you can now see why the plugin architecture is so > valuable, though. I'm very familiar with the benefits of the plugin architecture, but thanks for the review. There are three anti-spam plugins available, BayesIt and two others. One is called VampireX. It doesn't use bayes classification and only uses regex. My preference is Bayes and since I haven't heard any positive comments about this one, I haven't used it. http://www.softpedia.com/public/cat/10/3/3/10-3-3-161.shtml There is also one by Achim Winkler that is called Bayes Filter, I think. http://www.lkcc.org/achim/download/ It's described on TBDEV in this message. http://www.mail-archive.com/[EMAIL PROTECTED]/msg00532.html > SpamAssassin should at most be marking suspected spam with some kind > of subject alteration or header, and then you should let bayesit candle > it as normal. If you're filtering on modifications made by > SpamAssassin and not marking the filtered mails as junk for bayesit, > it will never learn. That's what I do. BayesIt still doesn't learn. I've also updated the kludges file on the off chance that the case of the headers mattered. I suspect, based on the number of people that seem to be having problems, there may be some issues with the plugins that haven't been worked out. It could be any number of things. At one time, there was a report that one version of BayesIt wasn't working on Win98 because the author was relying on some system variables that were Win2k and XP specific. That was fixed. Someone's reported that it took over 500 spam mails until it started working. Someone else reported it started working after 10 spam mails. Who knows? It never worked for me and I average 50 spam mails a day and I had both filters in place for several months. I don't really have the time right now to spend on trying to troubleshoot the plugins. I've uninstalled both BayesIt and Bayes Filter and will now try them out one at a time to see what's happening. Maybe
Re[3]: BayesIt
Hello Richard, Saturday, June 19, 2004, 2:33:38 AM, you wrote: RHS> Saturday, June 19, 2004, 2:13:08 AM, you wrote: aacu>> I change to POPFiel from weeks of frsutration with BayesIt slowing aacu>> down things, crashing the Bat etc. RHS> I'm using BayesIT, and have no problems with it. It's catching about RHS> 95% of the spam, which I hope will increase eventually, but even then RHS> that's only one or two a day that get through. The white/blacklist button is grayed out in my copy. As a work around I use a filter to retrieve the messages I would normally mark as whitelist from the Junk folder. Not an ideal situation... -- Best regards, Tony "Vacuum: A large, empty space where the pope lives." Current version is 2.11.02 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIt
Hello Graham, Monday, June 21, 2004, 9:22:21 AM, you wrote: GD> Hello Andre, GD> Saturday, June 19, 2004, 12:25:11 PM, you wrote: AW>> Hello Richard, AW>> On 19 Jun 2004 at 05:33:38 +0500 GMT [02:33 CEST] you wrote: RHS>>> I'm using BayesIT, and have no problems with it. It's catching about RHS>>> 95% of the spam, which I hope will increase eventually, but even then RHS>>> that's only one or two a day that get through. AW>> Mine is at 99.8% for last month and 99.94% for last week :) GD> I would be happy if I could catch 1 spam... :-( GD> I have SpamAssassin running on the mail server, it throws certain Spam into an IMAP GD> account for manual proofing - I mark all this and flag as Junk (training GD> BayesIt) GD> Spam that reaches TB also gets marked as Junk (more BayesIt training) GD> The problem is that BayesIt never catches spam on it's own !! GD> I did not have this problem with BayesIt 0.4g, I have followed the advice GD> to delete all previous dictionaries, but BayesIt just sits there and does GD> nothing I installed a newer version of Bayesit! yesterday, going from 0.4gm to 0.5.5. I see that the only difference is that you need to remove the earlier bases and that the training function in the configuration dialog is gone. I marked all the mails that I have in my Junk folders (about 25.000) and clicked "Mark as Junk" from the Specials Menu. That's the new way to train, it even shows a small dialog (if you have enabled it) that says training. Would have been fun to have some kind of documentation for 0.5.5, I found some in russian but babelfish.alstavista.com did not help me that much, and I did not understand anything of it :). If you do not have enough SPAM I could send you some :) for training. /Fredrik Current version is 2.11.02 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIt
On 21 Jun 2004 at 09:22:21 you wrote: GD> I would be happy if I could catch 1 spam... :-( GD> I have SpamAssassin running on the mail server, it throws certain Spam into an IMAP GD> account for manual proofing - I mark all this and flag as Junk (training GD> BayesIt) I don't think bayesit works with imap. GD> Spam that reaches TB also gets marked as Junk (more BayesIt training) So how many spam and non-spam messages have you marked? The information under preferences: does the size of the dictionaries increase? GD> The problem is that BayesIt never catches spam on it's own !! GD> I did not have this problem with BayesIt 0.4g, I have followed the advice GD> to delete all previous dictionaries, but BayesIt just sits there and does GD> nothing -- Gruß, Chenoa mailto:[EMAIL PROTECTED] "Organic chemistry is the chemistry of carbon compounds. Biochemistry is the study of carbon compounds that crawl." Current version is 2.11.02 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIt
On Wednesday, October 20, 2004, 2:10:40 AM, MikeD wrote: > and I should also mention that the newest version is 0.7.3 and > since you are going to have to go through all that anyway, you might > want to get this version before you go through all that. It is much > improved over the version that was shipping with TB (unless they have > caught up ) Thanks, will do. Do I find it on the Ritlabs website? Sorry for the belated acknowledgement of your reply: had computer troubles and didn't get around to reading this list for a while... -- Regards, G. mailto:[EMAIL PROTECTED] Using The Bat! Version 3.0.1.33 Windows XP Version 5 Build 2600 Current version is 3.0.1.33 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit
Hello MikeD, On Tuesday, November 02, 2004 at 10:56:50 GMT -0500 (which was 16:56:50 where I live), MikeD (3) wrote and made these valuable points on the subject of "Bayesit": > Hello Dan, > Tuesday, November 2, 2004, 8:46:34 AM, you wrote: DG>> Tue, 2 Nov 2004 13:31:10 +0200 (6:31 AM EST here) Dave Thomas wrote: >>> Where do I find the link to the latest [Bayesit] version > www.ritlabs.com/download/files3/bayesit/bayesit073.rar Here is a more recent version: www.ritlabs.com/download/files3/bayesit/bayesit074.rar -- Best regards, Dick ___ Using The Bat! v3.0.2.4 Rush + BayesIt! 0.7.4 on Windows XP 5.1 Build 2600 Service Pack 1 Current version is 3.0.1.33 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit
Hello Dave, Wednesday, November 3, 2004, 9:42:05 AM, you wrote: DT> Thanks Mike Always happy to be able to give back in some small way for all the help I have gotten -- Best regards, MikeDmailto:[EMAIL PROTECTED] Using The Bat! v3.0.2.1 on Windows ME 4.90 Build 3000 Current version is 3.0.1.33 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit Plugin
Hi John, JM> let it install it and I've been training it, but I just don't work JM> anymore, or never did for that mater. I guess I'm going to have to JM> find something else, I don't know why they chose to bundle a plugin JM> with TheBat that would take years of training just to get it to work. Like someone pointed out, BayesIt is hit or miss...it either works for you or it doesn't. I couldn't get it to work well for a long time. But on one install it just magically worked. I receive about 1200 e-mails daily, 30% SPAM. I have maintained an overall accuracy rate of 99.87% for 2 months now and never had a false positive. I have a quick template that automatically e-mails my BayesIt data for the previous day to myself. I went back and checked, over the past 40 days, I have 20 days that BayesIt scored a perfect 100% classification rate. There were some suggestions on the list I implemented that seem to have helped, like using the whitelist function to classify all the mail from groups like this and keeping the the "move to junk if score is" somewhere above 90. -- Mike Rourke :flag-us-tx: :flag-thailand: Windows XP Professional Service Pack 2 The Bat! 3.0.2.6 Current version is 3.0.1.33 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIt option settings
Sunday, April 18, 2004, 2:40:30 PM, you wrote: RHS> Before it was working normally. I'd been using it for only a month, RHS> but it was already averaging about 60%, and on a good day would hit RHS> 85-90%. If I can't get this version to work, I may go back to v.0.4. I gave up getting v.0.5 to work after re-installing several times, and have gone back to v.0.4. After re-installing and training it, it caught 100% this morning with no false positives. As long as it continues like this, there is no reason to try v.0.5 again. Current version is 2.10.01 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIT and BayesFilter
Paul, PJ>>> Can anyone point me to info regarding BayesIT and BayesFilter. PJ>>> What is the difference between them? >> BayesIT will actually work if you can get it installed. I've never >> been able to get the other one to do anything except grab program >> focus for a couple of seconds and then give me a OK dialog that needs >> to be dismissed saying, "One messages processed". PJ> Thanks; any tips on how to successfully get BayesIT installed? This is the problem; I have this addressed along with several other testers on TBBETA with no answer yet. The next thing on my list is to do a complete re-install of v3 and get it working. I don't think the latest Bayesit will even be recognized as a plugin by the TB v3.0.6 so don't even try it. I believe bayesit v061 will work with TB v3.0 as an upgrade from what is originally supplied with the full version of TB. That's all I know for now. -- Neal Laugman Using The Bat! v3.0 Beta/1 and on Windows 2000 5.0 Build 2195 Service Pack 4 Current version is 3.00.00 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIT and BayesFilter
Hello Paul, Monday, September 6, 2004, 2:13:39 PM, you wrote: PJ>>> Can anyone point me to info regarding BayesIT and BayesFilter. PJ>>> What is the difference between them? >> BayesIT will actually work if you can get it installed. I've never >> been able to get the other one to do anything except grab program >> focus for a couple of seconds and then give me a OK dialog that needs >> to be dismissed saying, "One messages processed". PJ> Thanks; any tips on how to successfully get BayesIT installed? Mostly it is a YMMV sort of thing at the moment. You install it and it works well or it does not. I have it (BayesIt 0.6.1) working on my system. I had some early problems because I installed it over an older version. The key there seems to be to completely remove all traces of the old one before installing and trying to train the new one. If you have never installed it, you may not have any problems. But as others have said, they did. It is it is a problem for you, it is easy enough to remove it and wait to see if the next release helps you. -- Best regards, MikeDmailto:[EMAIL PROTECTED] Using The Bat! v2.12.00 on Windows ME 4.90 Build 3000 Current version is 3.00.00 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIT! and filters
Hello Stuart, Saturday, October 16, 2004, 9:06:23 AM, you wrote: SC> Michael is using Version 3 which does not have the "alternative" tab. I guess I will have to bite the bullet soon and move up to 3 -- Best regards, MikeDmailto:[EMAIL PROTECTED] Using The Bat! v2.12.00 on Windows ME 4.90 Build 3000 Current version is 3.0.1.33 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit or Bayes Filter
Hello Group On Sunday, August 21, 2005, 8:33:48 PM, P. wrote: > So, BayseIt is definitely not working. I've tweaked the settings and > guess I'll wait for the onslaught of spam on Monday to see if that > helps. I found BayesIt very poor even after training. I have switched to K9 now and find it much better. -- Jeff Gaines Damerham Hampshire UK :Jeff_Gaines: Using TheBat! 3.51.10 Current version is 3.51.10 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: BayesIt web english web page
Hello MikeD, Sunday, September 26, 2004, 8:08:39 PM, you wrote: SMK>> I'm, using 06.6, which I thought was the latest version. BayesIt hasn't SMK>> worked well for me since the version that came with The Bat 2.12; I don't SMK>> remember its version number. > That would 0.5.11. It is what I continue to return to when I have > problems with a new version of the 0.6 tree. Last time I looked, it > was still available. 2.12 comes with 0.55. I know that because I recently installed that version and am still using the Bayesit version that comes with it. -- Best regards, Andre Current version is 3.00.00 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re: Re[3]: Bayesit or Bayes Filter
On 8/21/05, Jeff Gaines <[EMAIL PROTECTED]> wrote: > I found BayesIt very poor even after training. I have switched to K9 > now and find it much better. AOL that. I've never gotten BayesIt to work, and I'm not the most computer-illiterate person out there. When "c't Magazin" (renowned German computer mag) tested several mail clients, TB among them, they couldn't get it to work, either. Go figure. I've been using K9 for about two year now and find it great. It's tiny, very fast, and very reliable. Roman -- Current version is 3.51.10 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re: Re[3]: Bayesit or Bayes Filter
Jeff Gaines said... > Hello Group > > On Sunday, August 21, 2005, 8:33:48 PM, P. wrote: > > > So, BayseIt is definitely not working. I've tweaked the settings and > > guess I'll wait for the onslaught of spam on Monday to see if that > > helps. > > I found BayesIt very poor even after training. I have switched to K9 > now and find it much better. Yup. I've not had to use the white or black lists with K9 either. When using BayesIt, the lists became unmanageable. And you can't resize the dialog and why is it modal? Actually, thinking about it, there's a lot of modal nonsense going on in TB. Grrr. But, on a happy note, K9 is the dog's ;-) -- Best, Marc Current version is 3.51.10 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
Re[3]: Bayesit 0.5.2 Rules grey How to train?
On Tuesday, April 20, 2004 at 2:13:52 PM, you wrote: > Hello Marek, > Monday, April 19, 2004, 5:24:55 PM, you wrote: MM>> via options "Mark as Junk" and "Mark as not Junk" in Specials menu. > Since we have to use this now for all the training ... is there a way > to make these two functions more accessible ... like by assigning a > key to each? You can by using the standard keyboard shortcut additions dialogue thingy. Marten Gallagher -- Annery Kiln Web Design Delivering Information Effectively www.annerykiln.co.uk Web Design and Site Management Web Hosting and Print Design This e-mail is intended solely for the addressee and is strictly confidential. If you are not the addressee, please do not read, print, re-transmit, store or act in reliance on it or any attachments. Instead please e-mail it back to the sender and delete the message from your computer. The system used to send this message is permanently checking for viruses and malicious scripts. However, email transmission cannot be guaranteed to be secure or error free and annerykiln.co.uk accepts no liability for changes made to this e-mail (and any attachments) after it was sent or for viruses arising as a result of this e-mail transmission. Any unauthorised reproduction, dissemination, copying, disclosure, modification, distribution and/or publication of this e-mail message is strictly prohibited. mailto:[EMAIL PROTECTED] Current version is 2.10.01 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html