A Production Oriented Approach for Vandalism Detection in Wikidata - The Buffaloberry Vandalism Detector at WSDM Cup 2017
This work addresses the risk of misinformation spread in Wikidata, which is used by various systems including search engines, but it is incremental as it builds on prior methods.
The paper tackled the problem of vandalism detection in Wikidata by developing a fast and reliable prediction system to identify suspicious edits for human review, achieving top performance in the WSDM Cup 2017 competition.
Wikidata is a free and open knowledge base from the Wikimedia Foundation, that not only acts as a central storage of structured data for other projects of the organization, but also for a growing array of information systems, including search engines. Like Wikipedia, Wikidata's content can be created and edited by anyone; which is the main source of its strength, but also allows for malicious users to vandalize it, risking the spreading of misinformation through all the systems that rely on it as a source of structured facts. Our task at the WSDM Cup 2017 was to come up with a fast and reliable prediction system that narrows down suspicious edits for human revision. Elaborating on previous works by Heindorf et al. we were able to outperform all other contestants, while incorporating new interesting features, unifying the programming language used to only Python and refactoring the feature extractor into a simpler and more compact code base.