STiki: An Anti-Vandalism Tool for Wikipedia using Spatio-Temporal Analysis of Revision Metadata
Track: Demos
Authors: Andrew West, Sampath Kannan and Insup Lee
Slides: SLIDES
Abstract
STiki is an anti-vandalism tool for Wikipedia. Unlike similar tools, STiki does not rely on natural language processing (NLP) over the article or diff text to locate vandalism. Instead, STiki leverages spatio-temporal properties of revision metadata. The feasibility of utilizing such properties was demonstrated in our prior work, which found they perform comparably to NLP-e orts while being more efficient, robust to evasion, and language independent.
STiki is a real-time, on-Wikipedia implementation based on these properties. It consists of, (1) a server-side processing engine that examines revisions, scoring the likelihood each is vandalism, and, (2) a client-side GUI that presents likely vandalism to end-users for de nitive classi cation (and if necessary, reversion on Wikipedia). Our demonstration will provide an introduction to spatio-temporal properties, demonstrate the STiki software, and discuss alternative research uses for the open-source code.
Sidebar
wikisym: R...
- wikisym: Remember to tell all your graduate student friends and collaborators to apply for the #WikiSym 2012 doctoral symposium! http://t.co/nKOHjdk3
- wikisym: Hey you Wikipedia-studying PhD students, apply to the #WikiSym 2012 doctoral consortium with @blurky! http://t.co/nKOHjdk3
- wikisym: Don't forget, you have 7 weeks to prepare technology demos for everyone at @ArsElectronica to see! http://t.co/nKOHjdk3 #WikiSym
- wikisym: Glad that all you authors submitted. There are some outstanding paper submissions from authors across the globe! #WikiSym 2012