|
Title:
|
CALCULATING THE TRUSTWORTHINESS OF WIKIPEDIA ARTICLES USING DANTE METHODOLOGY |
|
Author(s):
|
Pierpaolo Dondio , Stephen Barrett , Stefan Weber |
|
ISBN:
|
972-8924-16-X |
|
Editors:
|
Pedro Isaías, Maggie McPherson and Frank Bannister |
|
Year:
|
2006 |
|
Edition:
|
1 |
|
Keywords:
|
Computational trust, Wikipedia, trust model, methodology, knowledge provenance. |
|
Type:
|
Full Paper |
|
First Page:
|
157 |
|
Last Page:
|
168 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
The problem of identifying useful and trustworthy information on the World Wide Web is becoming increasingly acute
as new tools such as wikis and blogs simplify and democratize publication. This digital content is often discussed and
criticised in comparison to centrally edited, printed resources, which are still considered to be the gold standard of
information. Despite the legitimate criticism of digital content generated by devolved communities, it is not hard to
predict that in the future the direct reliance on this material will expand. The problem of evaluating the trustworthiness of
this kind of content is thus crucial. The Wikipedia project represents the most successful and discussed example of such
online resources. The free encyclopaedia, entirely written collaboratively by an open community of users, now supports
800.000 registered user, delivers 900.000 articles in its English version alone, and it is one of the ten most visited web
sites. Recently, the Wikipedia foundation initiated the Wikipedia Education project, tasked to improve the quality of
articles with educational purposes. In this paper we present a method for evaluating the trustworthiness of a Wikipedia
article. The method, based on a paradigm called DANTE, has the characteristics of being automatic, able to evaluate a
page relying only on its present state, and being non invasive for the application. We report encouraging early results on
the automated evaluation of Wikipedia content. |
|
|
|
|
|
|
