On Sat, July 28, 2007 23:23, Mike Morrin wrote: > <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> > <html> > <head> > <meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type"> > <title></title> > </head> > <body bgcolor="#ffffff" text="#000000"> > Mark Hammond wrote: > <blockquote > cite="mid:[EMAIL PROTECTED]" > type="cite"> > <blockquote type="cite"> > <pre wrap="">That is high relative to the conventional wisdom, but I'm > questioning > the correctness of that wisdom. > </pre> > </blockquote> > <pre wrap=""><!----> > Check out this thread, which should give you a reasonable idea: > > <a class="moz-txt-link-freetext" > href="http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html";>http://mail.python.org/pipermail/spambayes-dev/2003-November/001578.html</a> > > </pre> > <blockquote type="cite"> > <pre wrap="">Perhaps its time to re-evaluate that statement? > </pre> > </blockquote> > <pre wrap=""><!----> > Google also shows anecdotal reports of poor results after an imbalance as > low as 2:1, so I don't think it would be responsible to re-evaluate that > statement until clear evidence was presented to the contrary. > </pre> > </blockquote> > I don't get a lot of ham, and currently have 55 ham and 580 spam in my > Spambayes database. Despite this, it seems to be working > admirably. > It is however very sensitive to just one spam mistakenly put into the > ham base, which then completely upsets the filtering.<br> > <br> > So if the perceived wisdom is that I need to balance the ratios, what > should I do? send myself ham? or not use spam from my unsure folder > for training? or get more friends???<br>
Get more friends. Definitely! ;-) (and don't use html to write emails) -- Amedee _______________________________________________ SpamBayes@python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
