Home > slashdot > Competition On Detecting Vandalism In Wikis

Competition On Detecting Vandalism In Wikis

September 26th, 2010 09:03 admin Leave a comment Go to comments

marpot writes “Recently, the 1st International Competition on Wikipedia Vandalism Detection (PDF) 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 (PDF) 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 (PDF) analyzes an edit’s context using WikiTrust.”

Source: Competition On Detecting Vandalism In Wikis

Related Articles:

  1. Competition On Detecting Vandalism In Wikis
  2. Competition Produces Vandalism Detection For Wikis
  3. Developing a Vandalism Detector For Wikipedia
  4. OpenStreetMap Reports Data Vandalism From Google-Owned IPs
  5. Detecting Chemicals Through Bone
blog comments powered by Disqus