VEWS: A Wikipedia Vandal Early Warning System

Abstract

We study the problem of detecting vandals on Wikipedia <i>before</i> any human or known vandalism detection system reports flagging potential vandals so that such users can be presented early to Wikipedia administrators. We leverage multiple classical ML approaches, but develop 3 novel sets of features. Our Wikipedia Vandal Behavior (WVB) approach uses a… (More)
DOI: 10.1145/2783258.2783367
View Slides

Topics

13 Figures and Tables

Statistics

05010015020162017
Citations per Year

Citation Velocity: 61

Averaging 61 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Blog articles referencing this paper

Slides referencing similar topics