Filipus Klutiero <[email protected]> wrote: > > I see that http://www.grouplens.org has moved on and their research > > (like http://www.grouplens.org/node/126 - "The recommendations that > > are most accurate according to the standard metrics are sometimes not > > the recommendations that are most useful to users") may be informative > > for anyone who thinks that message-voting will surely work. > > > Unless you're suggesting a recommendation system, I don't see how this > paper is relevant.
Various messages in this thread have suggested using the votes as the basis of a recommendation system for messages or authors. I think such a system would also exhibit the "similarity hole" mentioned in that paper. To be specific: it will prioritise what the voting groups already know, over what would be most useful to the project. However, that's just one example of the studies and - particularly if you've never tried GroupLens or a similar system - several of the papers are worth reading, illustrating the limits of item voting systems and the challenges to overcome. I believe those limits and challenges mean that wider moderation/facilitation would be more rewarding for the same effort. Hope that explains, -- MJ Ray (slef) Webmaster for hire, statistician and online shop builder for a small worker cooperative http://www.ttllp.co.uk/ http://mjr.towers.org.uk/ (Notice http://mjr.towers.org.uk/email.html) tel:+44-844-4437-237 -- To UNSUBSCRIBE, email to [email protected] with a subject of "unsubscribe". Trouble? Contact [email protected]
