19 July 2011
A fun modeling project from a group of physicists on Edit wars in Wikipedia:
We present a new, efficient method for automatically detecting severe conflicts `edit wars’ in Wikipedia and evaluate this method on six different language WPs. We discuss how the number of edits, reverts, the length of discussions, the burstiness of edits and reverts deviate in such pages from those following the general workflow, and argue that earlier work has significantly over-estimated the contentiousness of the Wikipedia editing process.
Burstiness is new to me and appears to be popular in studying communication networks. Bursty (?) processes have many occurrences in short interval and long gaps between these bursts. Where is the burstiness in the social sciences? Would it measure anything interesting?
Also, maybe I don’t look much at the acknowledgements from other disciplines, but I have never seen such a clear delineation of work contributed:
Sumi developed the main classifier, Yasseri the temporal profiles, and Rung selected the seed examples and generated the data for supervised training. Kornai advised on multilingual natural language processing and statistical analysis. Kertesz designed the research, advised on temporal studies and on modeling.