Difference between revisions of "Tell Me More: An Actionable Quality Model for Wikipedia"
m |
|||
| Line 11: | Line 11: | ||
== Overview == | == Overview == | ||
| − | In this paper authors address the problem of developing actionable quality models for Wikipedia, models whose features directly suggest strategies for improving the quality of a given article. Authors first survey the literature in order to understand the notion of article quality in the context of Wikipedia and existing approaches to automatically assess article quality. Authors then develop classification models with varying combinations of more or less actionable features, and find that a model that only contains clearly actionable features delivers solid performance. Lastly authors discuss the implications of these results in terms of how they can help improve the quality of articles across Wikipedia. | + | In this paper authors address the problem of developing actionable quality models for [[Wikipedia]], models whose features directly suggest strategies for improving the quality of a given [[Wikipedia article|article]]. Authors first survey the literature in order to understand the notion of article quality in the context of Wikipedia and existing approaches to automatically assess article quality. Authors then develop classification models with varying combinations of more or less actionable features, and find that a model that only contains clearly actionable features delivers solid performance. Lastly authors discuss the implications of these results in terms of how they can help improve the quality of articles across Wikipedia. |
[[Category:Scientific works]] | [[Category:Scientific works]] | ||
Revision as of 21:49, 20 June 2018
Authors | Morten Warncke-Wang Dan Cosley John Riedl |
|---|---|
Publication date | 2013 |
ISBN | 978-1-4503-1852-5 |
DOI | 10.1145/2491055.2491063 |
Links | Original Preprint |
Tell Me More: An Actionable Quality Model for Wikipedia - scientific work about Wikipedia quality published in 2013, written by Morten Warncke-Wang, Dan Cosley and John Riedl.
Overview
In this paper authors address the problem of developing actionable quality models for Wikipedia, models whose features directly suggest strategies for improving the quality of a given article. Authors first survey the literature in order to understand the notion of article quality in the context of Wikipedia and existing approaches to automatically assess article quality. Authors then develop classification models with varying combinations of more or less actionable features, and find that a model that only contains clearly actionable features delivers solid performance. Lastly authors discuss the implications of these results in terms of how they can help improve the quality of articles across Wikipedia.
