Automatic site training

[Chris Fortune]

> My general idea is to have each user create a ham and a spam maildir on
> the server where they place all mail which gets classified wrong in
> these dirs. I will then run a script each week or so which trains on
> these files so that the users will not have to do this by themselves.
>

I recommend IMAP.  See this: https://spameater.com/bayesian-IMAP.html


> My question is then: Are any of you running a similar setup and what are
> your experiences with this,

Yes.  Personal wordlists are the highest accuracy, but most prone to user error.  Excellent solution in your case.
Since your users are so similar in interests, you may also decide to take advantage of the new multi-wordlist capabilities and use
both an efficient central wordlist as well as small personal wordlists.