Portal nodes screening for large scale social networks

Xuening Zhu, Xiangyu Chang, Runze Li, Hansheng Wang

Research output: Contribution to journalArticle

Abstract

Network autoregression model (NAM), as a powerful tool to study user social behaviors on large scale social networks, has drawn great attention in recent years. In this paper, we are interested in identifying the influential users (i.e., portal nodes) in a social network under the framework of NAM. Especially, we consider the autoregression model that allows to have a heterogeneous and sparse network effect coefficients. Therefore, the portal nodes take influential powers which are corresponding to the nonzero network effect coefficients. A screening procedure is designed to screen out the portal nodes and the strong screening consistency is established theoretically. A quasi maximum likelihood method is applied to estimate the influential powers. The asymptotic normality of the resulting estimator is established. Further selection procedure is given by taking advantage of the local linear approximation algorithm. Extensive numerical studies are conducted by using a Sina Weibo dataset for illustration purpose.

Original languageEnglish (US)
Pages (from-to)145-157
Number of pages13
JournalJournal of Econometrics
Volume209
Issue number2
DOIs
StatePublished - Apr 1 2019

Fingerprint

Node
Autoregression
Social networks
Screening
Coefficients
Network effects
Estimator
Asymptotic normality
Approximation algorithms
Quasi-maximum likelihood
User studies

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

Zhu, Xuening ; Chang, Xiangyu ; Li, Runze ; Wang, Hansheng. / Portal nodes screening for large scale social networks. In: Journal of Econometrics. 2019 ; Vol. 209, No. 2. pp. 145-157.
@article{d0ec0f1e29ba48b286bf588a095e80f8,
title = "Portal nodes screening for large scale social networks",
abstract = "Network autoregression model (NAM), as a powerful tool to study user social behaviors on large scale social networks, has drawn great attention in recent years. In this paper, we are interested in identifying the influential users (i.e., portal nodes) in a social network under the framework of NAM. Especially, we consider the autoregression model that allows to have a heterogeneous and sparse network effect coefficients. Therefore, the portal nodes take influential powers which are corresponding to the nonzero network effect coefficients. A screening procedure is designed to screen out the portal nodes and the strong screening consistency is established theoretically. A quasi maximum likelihood method is applied to estimate the influential powers. The asymptotic normality of the resulting estimator is established. Further selection procedure is given by taking advantage of the local linear approximation algorithm. Extensive numerical studies are conducted by using a Sina Weibo dataset for illustration purpose.",
author = "Xuening Zhu and Xiangyu Chang and Runze Li and Hansheng Wang",
year = "2019",
month = "4",
day = "1",
doi = "10.1016/j.jeconom.2018.12.021",
language = "English (US)",
volume = "209",
pages = "145--157",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

Portal nodes screening for large scale social networks. / Zhu, Xuening; Chang, Xiangyu; Li, Runze; Wang, Hansheng.

In: Journal of Econometrics, Vol. 209, No. 2, 01.04.2019, p. 145-157.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Portal nodes screening for large scale social networks

AU - Zhu, Xuening

AU - Chang, Xiangyu

AU - Li, Runze

AU - Wang, Hansheng

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Network autoregression model (NAM), as a powerful tool to study user social behaviors on large scale social networks, has drawn great attention in recent years. In this paper, we are interested in identifying the influential users (i.e., portal nodes) in a social network under the framework of NAM. Especially, we consider the autoregression model that allows to have a heterogeneous and sparse network effect coefficients. Therefore, the portal nodes take influential powers which are corresponding to the nonzero network effect coefficients. A screening procedure is designed to screen out the portal nodes and the strong screening consistency is established theoretically. A quasi maximum likelihood method is applied to estimate the influential powers. The asymptotic normality of the resulting estimator is established. Further selection procedure is given by taking advantage of the local linear approximation algorithm. Extensive numerical studies are conducted by using a Sina Weibo dataset for illustration purpose.

AB - Network autoregression model (NAM), as a powerful tool to study user social behaviors on large scale social networks, has drawn great attention in recent years. In this paper, we are interested in identifying the influential users (i.e., portal nodes) in a social network under the framework of NAM. Especially, we consider the autoregression model that allows to have a heterogeneous and sparse network effect coefficients. Therefore, the portal nodes take influential powers which are corresponding to the nonzero network effect coefficients. A screening procedure is designed to screen out the portal nodes and the strong screening consistency is established theoretically. A quasi maximum likelihood method is applied to estimate the influential powers. The asymptotic normality of the resulting estimator is established. Further selection procedure is given by taking advantage of the local linear approximation algorithm. Extensive numerical studies are conducted by using a Sina Weibo dataset for illustration purpose.

UR - http://www.scopus.com/inward/record.url?scp=85060332580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060332580&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2018.12.021

DO - 10.1016/j.jeconom.2018.12.021

M3 - Article

AN - SCOPUS:85060332580

VL - 209

SP - 145

EP - 157

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -