Wikipedia Revision Scoring as a Service

Data Skeptic

Episode | Podcast

Date: Fri, 18 Dec 2015 14:30:00 +0000

<p>In this interview with <a href="http://halfaker.info/">Aaron Halfaker</a> of the Wikimedia Foundation, we discuss his research and career related to the study of Wikipedia. In his paper <a href="https://www-users.cs.umn.edu/~halfak/publications/The_Rise_and_Decline/"> The Rise and Decline of an open Collaboration Community</a>, he highlights a trend in the declining rate of active editors on Wikipedia which began in 2007. I asked Aaron about a variety of possible hypotheses for the phenomenon, in particular, how automated quality control tools that revert edits automatically could play a role. This lead Aaron and his collaborators to develop <a href="http://www-users.cs.umn.edu/~halfak/publications/Snuggle/">Snuggle</a>, an optimized interface to help Wikipedians better welcome new comers to the community.</p> <p>We discuss the details of these topics as well as <a href="https://meta.wikimedia.org/wiki/Objective_Revision_Evaluation_Service"> ORES</a>, which provides <a href="https://meta.wikimedia.org/wiki/Research:Revision_scoring_as_a_service"> revision scoring as a service</a> to any software developer that wants to consume the output of their machine learning based scoring.</p> <p>You can find Aaron on Twitter as <a href="https://twitter.com/halfak">@halfak</a>.</p>