Wiki-Watchdog: Anomaly Detection in Wikipedia Through a Distributional Lens

Wiki-Watchdog: Anomaly Detection in Wikipedia Through a Distributional Lens - scientific work related to Wikipedia quality published in 2011, written by Chrisil Arackaparambil and Guanhua Yan.

Overview

Wikipedia has become a standard source of reference online, and many people (some unknowingly) now trust this corpus of knowledge as an authority to fulfil their information requirements. In doing so they task the human contributors of Wikipedia with maintaining the accuracy of articles, a job that these contributors have been performing admirably. Authors study the problem of monitoring the Wikipedia corpus with the goal of emph{automated, online} anomaly detection. Authors present Wiki-watchdog, an efficient emph{distribution-based} methodology that monitors distributions of revision activity for changes. Authors show that using methods it is possible to detect the activity of bots, flash events, and outages, as they occur. Authors methods are proposed to support the monitoring of the contributors. They are useful to speed-up anomaly detection, and identify events that are hard to detect manually. Authors show the efficacy and the low false-positive rate of methods by experiments on the revision history of Wikipedia. Authors results show that distribution-based anomaly detection has a higher detection rate than traditional methods based on either volume or entropy alone. Unlike previous work on anomaly detection in information networks that worked with a static network graph, methods consider the network emph{as it evolves} and monitors properties of the network for changes. Although methodology is developed and evaluated on Wikipedia, authors believe it is an effective generic anomaly detection framework in its own right.