Hello Code, On 11 Jul 2004 at 10:28:06 -0700 GMT [19:28 CEST] you wrote:
C2> 1. Is ongoing training necessary only when BayesIt misses spam or C2> mis-identifies non-spam, or is something more required? You only need to correct mistakes. C2> 2. Is there a point where training BayesIt doesn't noticeably improve C2> accuracy, and in fact slows down processing because of of the size of C2> its dictionaries? If so, where is that point? C2> 3. You guys describe your own accuracy stats in terms of "99.8% for C2> last month", "99.94% for last week" and such. Where are you getting C2> these stats? Preferences->Plugins->Information -- Cheers, Andre :andre: "Our problems are man-made, therefore they may be solved by man. And man can be as big as he wants. No problem of human destiny is beyond human beings." ________________________________________________ Current version is 2.11.02 | 'Using TBUDL' information: http://www.silverstones.com/thebat/TBUDLInfo.html
