With Few Eyes, All Hoaxes are Deep
Open Access
- 1 November 2018
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 2 (CSCW) , 1-18
Abstract
Quality control is critical to open production communities like Wikipedia. Wikipedia editors enact border quality control with edits (counter-vandalism) and new article creations (new page patrolling) shortly after they are saved. In this paper, we describe a long-standing set of inefficiencies that have plagued new page patrolling by drawing a contrast to the more efficient, distributed processes for counter-vandalism. Further, to address this issue, we demonstrate an effective automated topic model based on a labeling strategy that leverages a folksonomy developed by subject specific working groups in Wikipedia (WikiProject tags) and a flexible ontology (WikiProjects Directory) to arrive at a hierarchical and uniform label set. We are able to attain very high fitness measures (macro ROC-AUC: 95.2%, macro PR-AUC: 74.5%) and real-time performance using word2vec-based features. Finally, we present a proposal for how incorporating this model into current tools will shift the dynamics of new article review positively.Keywords
This publication has 12 references indexed in Scilit:
- Interpolating Quality Dynamics in Wikipedia and Demonstrating the Keilana Effect2017
- Building Automated Vandalism Detection Tools for Wikidata2017
- Topic Modeling for Short Texts with Auxiliary Word Embeddings2016
- Tell me more2013
- When the levee breaks2013
- The work of sustaining order in wikipedia2010
- Automatic Vandalism Detection in Wikipedia2008
- Random ForestsMachine Learning, 2001
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- A training algorithm for optimal margin classifiers1992