Re: [R] Discussion: Spam on R-help

2003-08-04 Thread Christian Hennig
Hi Ted,

the R-help list is maintained by Martin Maechler, ETH Zurich, 
who is not at work at the moment. We had various computer problems at the
ETH in the last week. It may be that the spam filter broke down somehow and
Martin is not here to fix it. I think the reason for the lots of spam are
temporary technical problems and I hope we will have a filtered mailing
list again in one or two weeks.

Christian

On Mon, 4 Aug 2003 [EMAIL PROTECTED] wrote:

 [re-sending this one since it apparently didn't get through yesterday]
 
 Hi Folks,
 
 I just had a look at the r-help archive for the still-young month of
 August, and happened to notice that out of 49 postings there, 20 were
 assorted spam of all-too-familiar types.
 
 I'm wondering (discussion point) whether this might suggest that the
 list should adopt a more restrictive policy. Apparently, as things
 now stand, anyone may post to the list.
 
 I faced the same problem some months ago when two lists which I run
 ([EMAIL PROTECTED] and [EMAIL PROTECTED]) were being hit by spam
 at a rate which was becoming irritating. With great reluctance, I came
 to the conclusion that the lists would have to be restricted to posting
 by members only. This has had the knock-on effect that both spam and
 also occasional genuine worthwhile postings by non-members end up being
 sent to me for approval. Fortunately in the case of these lists, the
 frequency of this remains at an acceptable level -- say a dozen or so a
 week, of which almost all are spam and are easily dealt with, with no
 regrets if there's any delay before I get round to it. Also there are
 not huge numbers of subscribers -- the overall level of traffic is
 relatively low.
 
 Another knock-on effect is tbat when I get a subscription request from
 an email address that is not obviously bona-fide, I feel obliged to
 send off a mail to that address asking for confirmation of genuine
 interest in Linux (I have a pro-forma template for this). This is
 to prevent people subscribing to the list in order either to send out
 spam via the list or to harvest email addresses of list subscribers.
 For the same reasons, access to the lists' archives and to subscriber
 lists is password-restricted to subscribers.
 
 It is likely to be otherwise with r-help. This has a fairly high level
 of traffic, many people may welcome the opportunity to post messages
 without subscribing, and the list-owners might find themselves forced to
 devote more time than they would welcome to dealing not only with spam
 but also with non-member postings, if the list became members-only.
 There are many subscribers: this too would add to the list-owners' burden
 if they had to manage all that.
 
 On the other hand there is the possibility of spam-blocking software.
 This works up to a point, and provided the amount of spam that slipped
 through was small it could be an acceptable solution. At the same time,
 it's all too easy for genuine messages to get blocked if the spam-filter
 triggers are comprehensive enough to trap most spam (in a statistical
 context, SEX may be a factor; and there are many other triggers e.g. in
 the 'cluster' package).
 
 Yet again, people can simply accept that spam, like flies in Summer,
 is one of those irritations that must simply be ignored: just hit
 delete.
 
 Anyway, as I said, a point for discussion. What do people think?
 
 Best wishes to all,
 Ted.
 
 PS: Just to make clear that I'm not _complaining_ about receiving spam
 via r-help. Those 20 messages would be only a tiny fraction of the
 hundreds of times I have hit delete since 1 August!
 
 
 
 E-Mail: (Ted Harding) [EMAIL PROTECTED]
 Fax-to-email: +44 (0)870 167 1972
 Date: 03-Aug-03   Time: 13:39:17
 -- XFMail --
 
 __
 [EMAIL PROTECTED] mailing list
 https://www.stat.math.ethz.ch/mailman/listinfo/r-help
 

-- 
***
Christian Hennig
Seminar fuer Statistik, ETH-Zentrum (LEO), CH-8092 Zuerich (currently)
and Fachbereich Mathematik-SPST/ZMS, Universitaet Hamburg
[EMAIL PROTECTED], http://stat.ethz.ch/~hennig/
[EMAIL PROTECTED], http://www.math.uni-hamburg.de/home/hennig/
###
ich empfehle www.boag.de

__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help


RE: [R] Discussion: Spam on R-help

2003-08-04 Thread M. Edward Borasky
Well ... I have SpamCop on my incoming e-mail, and it snagged every one of
the beasts ... *And* reported them to whatever authorities SpamCop has
available to handle spam reports. Those few ISPs that listen to SpamCop
reports will chastise the spammers for their aggression.

SpamCop costs $30US a year. If there's a way to hook it up to the incoming
port on the R-help mailing list, I'd be willing to contribute $30. It also
catches viruses for those of us blessed (?) with Windows.

-- 
M. Edward (Ed) Borasky
mailto:[EMAIL PROTECTED]
http://www.borasky-research.net
 
Suppose that tonight, while you sleep, a miracle happens - you wake up
tomorrow with what you have longed for! How will you discover that a miracle
happened? How will your loved ones? What will be different? What will you
notice? What do you need to explode into tomorrow with grace, power, love,
passion and confidence? -- L. Michael Hall, PhD

__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help


RE: [R] Discussion: Spam on R-help

2003-08-04 Thread Prof Brian Ripley
Christian Hennig has already replied that there have been serious
computing disruptions at ETH (as can be seen from the delays on the R
lists), and Martin Maechler is away at present.

Normally there is extensive spam protection in place, and Martin has done
a lot of work to ensure that you don't see things.  It really is unfair to
Martin in particular to jump in on one of the rare occasions when things
go wrong.  He deserves praise for the normal situation, and perhaps we 
need to turn the checks off from time to time so people appreciate the 
excellent work done on their behalf.

Can we please drop this thread until Martin returns and has the time to 
investigate?

On Mon, 4 Aug 2003, M. Edward Borasky wrote:

 Well ... I have SpamCop on my incoming e-mail, and it snagged every one of
 the beasts ... *And* reported them to whatever authorities SpamCop has
 available to handle spam reports. Those few ISPs that listen to SpamCop
 reports will chastise the spammers for their aggression.
 
 SpamCop costs $30US a year. If there's a way to hook it up to the incoming
 port on the R-help mailing list, I'd be willing to contribute $30. It also
 catches viruses for those of us blessed (?) with Windows.

-- 
Brian D. Ripley,  [EMAIL PROTECTED]
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel:  +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UKFax:  +44 1865 272595

__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help