Bayesian Inference of Online Social Network Statistics via Lightweight Random Walk Crawls - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2015

Bayesian Inference of Online Social Network Statistics via Lightweight Random Walk Crawls

Abstract

Online social networks (OSN) contain extensive amount of information about the underlying society that is yet to be explored. One of the most feasible technique to fetch information from OSN, crawling through Application Programming Interface (API) requests, poses serious concerns over the the guarantees of the estimates. In this work, we focus on making reliable statistical inference with limited API crawls. Based on regenerative properties of the random walks, we propose an unbiased estimator for the aggregated sum of functions over edges and proved the connection between variance of the estimator and spectral gap. In order to facilitate Bayesian inference on the true value of the estimator, we derive the approximate posterior distribution of the estimate. Later the proposed ideas are validated with numerical experiments on inference problems in real-world networks.
Fichier principal
Vignette du fichier
RR-8793.pdf (952.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01216285 , version 1 (16-10-2015)
hal-01216285 , version 2 (19-10-2015)
hal-01216285 , version 3 (19-10-2015)
hal-01216285 , version 4 (17-12-2015)

Identifiers

Cite

Konstantin Avrachenkov, Bruno Ribeiro, Jithin K. Sreedharan. Bayesian Inference of Online Social Network Statistics via Lightweight Random Walk Crawls. [Research Report] RR-8793, Inria Sophia Antipolis; Purdue University. 2015. ⟨hal-01216285v4⟩
209 View
114 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More