2010/11/30 by Vicenç Gómez, Hilbert J. Kappen, Andreas Kaltenbrunner · 1 citation
Physics and Astronomy · Computer Science · #physics.data-an #cs.SI #physics.soc-ph
paper · pdf · doi:10.1145/1995966.1995992
published as 22nd ACM conference on hypertext and hypermedia (HT 2011) · 10 pages, 11 figures
arxiv created 2011/04/15 · arxiv updated 2012/03/06
We analyze the structure and evolution of discussion cascades in four popular websites: Slashdot, Barrapunto, Meneame and Wikipedia. Despite the big heterogeneities between these sites, a preferential attachment (PA) model with bias to the root can capture the temporal evolution of the observed trees and many of their statistical properties, namely, probability distributions of the branching factors (degrees), subtree sizes and certain correlations. The parameters of the model are learned efficiently using a novel maximum likelihood estimation scheme for PA and provide a figurative interpretation about the communication habits and the resulting discussion cascades on the four different websites.