On Thu, Oct 14, 2004 at 09:05:56AM -0700, Robin Lynn Frank wrote: > simply uncomment those we need to change. In other words, we do find a > greater need to increase scores. They may be statistically valid, but > there may also be a reason the phrase, "lies, damn lies and statistics", > was uttered long ago. ;-)</2cents>
A thing people (in general) seem to miss about SA is that like a lot of complex software, it's made available with default settings that generically work pretty well, but could be customized for your environment to make it work better. There's this kind of expectation out there that SA should just work without needing to do anything. ;) This is why on the "low side" you can just hand modify your scores, or for the "high side" we give out the software to generate message hit results (mass-check) and to generate the scores (perceptron) -- then you can take your own corpus and generate scores that best match the mail you receive. -- Randomly Generated Tagline: "My spleen is twice the size of a normal human spleen. This isn't such a big deal right now, but after I'm dead ... There's going to be a bidding war." - Dave Foley, Kids in the Hall
pgpNyREHHqOUB.pgp
Description: PGP signature
