[R] R-help "spam" detection; please help the moderators

[Martin Maechler]

Dear readers of R-help

as most of you will *not* be aware, R-help has continued to work the
way it does, only thanks to a dozen of volunteers,
see https://stat.ethz.ch/mailman/listinfo/r-help .

The volunteers manually moderate e-mails that "look like spam" (and
sometimes are and sometimes are not).
While much more than 90% of the spam is filtered out long before
a human sees it, with the increasing sophistication of spammers,
manual intervention has deemed to be necessary and served the
community very well.

OTOH, in recent weeks, the amount of work for the volunteers has
increased, mainly because an increasingly number of non-spam postings are
erronously tagged as "possibly spam".
We have discussed about this and done some analysis and found
that most of these message that produce a considerable amount of
extra work share two properties :
 1) they are posted via Nabble  {which *always* attaches a small
    	     	    		 pro-Nabble spam at the end of the message}
 2) the e-mail address of the sender is from a freemail
    provider, quite often 'at gmail dot com', and often the part
    *before* the '@' (at-sign) ends with digits.

We hereby ask those among you who use a freemail account to
please no longer post via nabble.

Thank you for your support of R-help, *the* "community mailing
list" of the R project since even before that project existed
"formally", namely since 1997-04-01,
today 13 years and two months.

Martin Maechler, ETH Zurich
(and R-help creator and principal manager)