Submissions/Spatio-Temporal Analysis of Revision Metadata and the STiki Anti-Vandalism Tool
From Wikimania 2010 • Gdańsk, Poland • July 9-11, 2010
This is an open submission for Wikimania 2010.
- Title of the submission
- Spatio-Temporal Analysis of Revision Metadata and the STiki Anti-Vandalism Tool
- Type of submission (workshop, tutorial, panel, presentation)
- Author of the submission
- Andrew G. West (west.andrew.g)
- E-mail address or username (if username, please confirm email address in Special:Preferences)
- westand [at] cis [dot] upenn [dot] edu
- Country of origin
- United States of America
- Affiliation, if any (organization, company etc.)
- University of Pennsylvania
- Personal homepage or blog
- Abstract (please use no less than 300 words to describe your proposal)
- STiki is an anti-vandalism tool for Wikipedia. Unlike similar tools (in academia), 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-efforts 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 definitive classification (and if necessary, reversion on Wikipedia). Our presentation will provide an introduction to spatio-temporal properties, demonstrate the STiki software, and discuss alternative uses for the open-source code. (Note: Existing on-Wikipedia tools, (e.g. Huggle), do utilize metadata. STiki adds a level of quantification and machine-learning not seen in such software).
- Track (People and Community/Knowledge and Collaboration/Infrastructure)
- People and Community (many of the edit classification features are actually reputations, that encode historical behavior of editors, articles, and spatial groupings thereof).
- Will you attend Wikimania if your submission is not accepted?
- A similar presentation (more academic) is being given at WikiSym, immediately preceeding WikiMania (see below). Thus, I will be in Gdansk and at least partially attending Wikimania.
- Slides or further information (optional)
- For scheduling purposes, if this presentation were to be accepted, it would be beneficial (for me) if it were to occur early in the programme.
- Brief description of the presentation/demo being given at WikiSym. Note that the academic rigor and focus would be adjusted for a WikiMania audience.
If you are interested in attending this session, please sign with your username below. This will help reviewers to decide which sessions are of high interest. Sign with four tildes. (~~~~).