In my application (C #), I need to filter emails based on their contents. If the email is double, you must send it to the specified email address, if it is a regular email address, I must send it to another email address.
I looked through the emails that came in and compiled a list of common words that appear in the subject line for double signatures (10-20 words). For each letter I sent, I checked if any of these words contained any of the words, and if they, where more than 2-3, depending on the length of the object, I decided that it was a failure. The problem was that this basic version did not work.
I read about spam filters (basically, what I want to do is similar.), And after searching for some examples on the Internet, I found some based on Bayesian networks. The problem with this solution is that I needed to feed a lot of training materials, which I don’t have yet.
How can I filter these letters based on the content + subject or just subject, without requiring a lot of training material?
EDIT: I want to perform filtering at the email server level.
source
share