We propose and evaluate QuWi (Quality in Wikipedia), a framework for quality control in Wikipedia. We build upon a previous proposal by Mizzaro [11], who proposed a method for substituting and/or complementing peer review in schol- arly publishing. Since articles in Wikipedia are never fin- ished, and their authors change continuously, we define a modified algorithm that takes into account the different do- main, with particular attention to the fact that authors con- tribute identifiable pieces of information that can be further modified by other authors. The algorithm assigns quality scores to articles and con- tributors. The scores assigned to articles can be used, for instance, to let the reader understand how reliable are the articles he or she is looking at, or to help contributors in identifying low quality articles to be enhanced. The scores assigned to users measure the average quality of their con- tributions to Wikipedia and can be used, for instance, for conflict resolution policies based on the quality of involved users. Our proposed algorithm is experimentally evaluated by analyzing the obtained quality scores on articles for deletion and featured articles, also on six temporal Wikipedia snap- shots. Preliminary results demonstrate that the proposed algorithm seems to appropriately identify high quality and low quality articles, and that good quality authors produce more long-lived contributions than low quality authors.

QuWi: Quality Control in Wikipedia

DELLA MEA, Vincenzo;MIZZARO, Stefano
2009-01-01

Abstract

We propose and evaluate QuWi (Quality in Wikipedia), a framework for quality control in Wikipedia. We build upon a previous proposal by Mizzaro [11], who proposed a method for substituting and/or complementing peer review in schol- arly publishing. Since articles in Wikipedia are never fin- ished, and their authors change continuously, we define a modified algorithm that takes into account the different do- main, with particular attention to the fact that authors con- tribute identifiable pieces of information that can be further modified by other authors. The algorithm assigns quality scores to articles and con- tributors. The scores assigned to articles can be used, for instance, to let the reader understand how reliable are the articles he or she is looking at, or to help contributors in identifying low quality articles to be enhanced. The scores assigned to users measure the average quality of their con- tributions to Wikipedia and can be used, for instance, for conflict resolution policies based on the quality of involved users. Our proposed algorithm is experimentally evaluated by analyzing the obtained quality scores on articles for deletion and featured articles, also on six temporal Wikipedia snap- shots. Preliminary results demonstrate that the proposed algorithm seems to appropriately identify high quality and low quality articles, and that good quality authors produce more long-lived contributions than low quality authors.
2009
9781605584881
File in questo prodotto:
File Dimensione Formato  
p27-cusinatoA.pdf

non disponibili

Tipologia: Altro materiale allegato
Licenza: Non pubblico
Dimensione 992.97 kB
Formato Adobe PDF
992.97 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/882129
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 19
  • ???jsp.display-item.citation.isi??? 9
social impact