Competition On Detecting Vandalism In Wikis

[sl4shd0t]

marpot writes "Recently, the 1st International Competition on Wikipedia Vandalism Detection finished: 9 groups (5 from the USA, 1 affiliated with Google) tried their best in detecting all vandalism cases from a large-scale evaluation corpus. The winning approach detects 20% of all vandalism cases without misclassifying regular edits; moreover, it can be adjusted to detect 95% of the vandalism edits while misclassifying only 30% of all regular edits. Thus, by applying both settings, manual double-checking would only be required on 34% of all edits. Nothing is known, yet, whether the rule-based bots on Wikipedia can compete with this machine learning-based strategy. Anyway, there is still a lot potential for improvements since the top 2 detectors use entirely different detection paradigms: the first analyzes an edit's content, whereas the second analyzes an edit's context using WikiTrust."http://a.fsdn.com/sd/facebook_icon_large.png (http://www.facebook.com/sharer.php?u=http%3A%2F%2Fdevelopers.slashdot.org% 2Fstory%2F10%2F09%2F26%2F1443206%2FCompetition-On-Detecting-Vandalism-In-Wikis) http://a.fsdn.com/sd/twitter_icon_large.png (http://twitter.com/home?status=+Competition+On+Detecting+Vandalism+In +Wikis%3A+http%3A%2F%2Fbit.ly%2Fdg5ald)
Read more of this story (http://developers.slashdot.org/story/10/09/26/1443206/-Competition-On-Detecting-Vandalism-In-Wikis?from=rss) at Slashdot.
http://feedads.g.doubleclick.net/~at/QvixjE1hGIBKw0EoKSPP70k73DM/0/di</img> (http://feedads.g.doubleclick.net/~at/QvixjE1hGIBKw0EoKSPP70k73DM/0/da)
http://feedads.g.doubleclick.net/~at/QvixjE1hGIBKw0EoKSPP70k73DM/1/di</img> (http://feedads.g.doubleclick.net/~at/QvixjE1hGIBKw0EoKSPP70k73DM/1/da)
http://feeds.feedburner.com/~r/Slashdot/slashdotDevelopers/~4/eXLFcnpAwkc

More... (http://rss.slashdot.org/~r/Slashdot/slashdotDevelopers/~3/eXLFcnpAwkc/-Competition-On-Detecting-Vandalism-In-Wikis)