I'm not really involved with Wikipedia, but it's how (learning) spam
detection bots work.
The big difference is the form of the content: OL has many small fields,
Wikipedia one big text field per item. I think they need different
indicators, but to learn from Wikipedia's approach isn't a bad idea :)
Using the Recent Changes API spam can be handled after submission pretty
quickly.
One could also think of giving users positive feedback on good edits
("thanks for correcting 'Wahsington' to 'Washington'!"), although bot
compliments have an ethical aspect that needs to be thought through :)
Ben
On 31 January 2013 17:29, Karen Coyle <[email protected]> wrote:
> Ben, is this what wikipedia does? Because they detect spam very quickly
> and I believe much of the detection is through bots. In any case, it is
> obvious to me that something like this is needed on OL. In fact, because
> it is wiki-like, there may be many things that can be learned from the
> wikipedia experience. Fortunately we don't have the same level of
> controversy to deal with -- mostly idiot spammers.
>
> kc
>
> On 1/31/13 5:56 AM, Ben Companjen wrote:
> > Hi all,
> >
> > Last night I wrote down [1] some ideas for learning to detect "bad" (and
> > good) edits. They're not brilliant or new, but hopefully inspiring to
> > anyone thinking of building some sort of bot to learn how (not) to edit
> > the catalogue. I'm envisioning semi-autonomous bots that suggest
> > corrections and in the long run fully autonomous bots to do repetitive
> > editing tasks
> >
> > It's really useful that the complete history is available. Machine
> > learning algorithms can use it to find patterns of bad edits to revert
> > (or even stop from happening) and good edits that can be applied to
> > other records.
> >
> > Has anyone ever tried to apply machine learning to OL?
> > Any comments?
> >
> > Ben
> >
> > [1]
> >
> http://ben.companjen.name/2013/01/finding-bad-edits-in-the-open-library-catalogue-ideas/
> >
> >
> > _______________________________________________
> > Ol-tech mailing list
> > [email protected]
> > http://mail.archive.org/cgi-bin/mailman/listinfo/ol-tech
> > To unsubscribe from this mailing list, send email to
> [email protected]
> >
>
> --
> Karen Coyle
> [email protected] http://kcoyle.net
> ph: 1-510-540-7596
> m: 1-510-435-8234
> skype: kcoylenet
> _______________________________________________
> Ol-tech mailing list
> [email protected]
> http://mail.archive.org/cgi-bin/mailman/listinfo/ol-tech
> To unsubscribe from this mailing list, send email to
> [email protected]
>
_______________________________________________
Ol-tech mailing list
[email protected]
http://mail.archive.org/cgi-bin/mailman/listinfo/ol-tech
To unsubscribe from this mailing list, send email to
[email protected]
