At 02:44 AM 8/31/2005, Beast wrote:
3. I have train hundreds (or thousands) spam/ham mail to sa-learn but it
seems it still not quite good detecting non-english mail.
Because SpamAssassin is based on the english language. SpamAssassin
doesn't know that in (example) Language X that "blahblahblah" means
"Hello, it's your brother. How is the family?" but "blabblabscoobydoo"
means "enlarge your ....."
That means using bayes filter for non-english is useless?
No, the bayes will be fine.
No it means that most of the body-text rules are useless. Your SA will be
limited to bayes, network checks, and message formating rules only.
But SA isn't meant to work well based on bayes alone.
