WikiWarMonitor |
Harnessing ICT - enabled collective social behaviour |
|
This webpage is dedicated to a project called WikiWarMonitor, as a part of the European Comission FP7 FET-Open supported project called ICTeCollective. Here we release datasets, software, and some results of our "Wikipedia editorial war" detection and ranking algorithm. |
|
Problem: Our general aim in this project is to locate, rank, characterise, predict and find ways to resolve Wikipedia edit warrings. To this end, we define a controversy measure M, which quantifies size and intensity of the edit warring taking place at a certain time and on a certain article. Using human judgment, we calibrate M such that the articles with an aggregated M larger/smaller than a threshold, could be considered as controversial/peacful articles. For a short description, please see this paper, and for more details please take a look at our publications listed below. | MSNBC: Wikipedia is editorial warzone, says study BBC Spanish: Las guerras de Wikipedia Decoded Science: Wikipedia Wars: Implications for Building Consensus University of Oxford: Mathematical model 'describes' how online conflicts are resolved Phys.org: Conflicts in Wikipedia now modelled by statistical physicists |
Procedure: Our code starts by parsing the Wikipedia dumps available by Wikimedia Foundation to produce what we call "light dumps" which only contains the timestamp , user name, a revision ID which is uniquely assigned to versions with the similar text hash-code. This makes us able to perform many different analysis and measurements on articles history needless of handling the Huge Wikipedia dumps. In the next step we use a separate code to calculate the controversy measure M based on the light dumps produced in the previous step. |
|
||||||||||||||||||||||||||
Who we are: Taha Yasseri, Robert Sumi, András Rung, János Török, András Kornai, János Kertész from Budapest University of Technology and Economis and Hoda Sepehri Rad from University of Alberta. |