A particle-learning-based approach to estimate the influence matrix of online social networks

Luis E. Castro, Nazrul I Shaikh

Research output: Contribution to journalArticle

Abstract

Knowing the extent of influence an agent exerts over the other agents over online social networks such as Twitter and Facebook is important as it helps identify opinion leaders and predict how opinions are likely to evolve. However, this information regarding the extent of influence exerted by agents on each other is difficult to obtain as it is unobservable and the data available to estimate it is scarce, often incomplete, and noisy. Further, the number of unknown parameters that need to be estimated to infer the extent of influence between any given pair of agents is very large. A particle-learning-based algorithm is proposed to estimate the influence matrix that indicates the extent of influence any agent exerts on any other in a social network. Computational studies have been used to determine the efficiency, learning rates and asymptotic properties, and robustness (to missing information) of the proposed particle learning algorithms. The results indicate that the proposed algorithm shows fast convergence rates, yields efficient estimates of the influence matrix, is scalable, and is robust to incomplete information. Further, the network topology, and not just the network size, impacts the learning rate. The learning rate also slows down as the percentage of missing information increases.

Original languageEnglish (US)
Pages (from-to)1-18
Number of pages18
JournalComputational Statistics and Data Analysis
Volume126
DOIs
StatePublished - Oct 1 2018

Fingerprint

Social Networks
Learning Rate
Estimate
Learning algorithms
Incomplete Information
Network Topology
Unknown Parameters
Fast Algorithm
Asymptotic Properties
Topology
Percentage
Convergence Rate
Influence
Learning
Learning Algorithm
Likely
Robustness
Predict

Keywords

  • Influence estimation
  • Learning
  • Opinion dynamics
  • Particle filter
  • Social networks

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Mathematics
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

A particle-learning-based approach to estimate the influence matrix of online social networks. / Castro, Luis E.; Shaikh, Nazrul I.

In: Computational Statistics and Data Analysis, Vol. 126, 01.10.2018, p. 1-18.

Research output: Contribution to journalArticle

@article{1fe0509b052b4803b89f26c500d512ea,
title = "A particle-learning-based approach to estimate the influence matrix of online social networks",
abstract = "Knowing the extent of influence an agent exerts over the other agents over online social networks such as Twitter and Facebook is important as it helps identify opinion leaders and predict how opinions are likely to evolve. However, this information regarding the extent of influence exerted by agents on each other is difficult to obtain as it is unobservable and the data available to estimate it is scarce, often incomplete, and noisy. Further, the number of unknown parameters that need to be estimated to infer the extent of influence between any given pair of agents is very large. A particle-learning-based algorithm is proposed to estimate the influence matrix that indicates the extent of influence any agent exerts on any other in a social network. Computational studies have been used to determine the efficiency, learning rates and asymptotic properties, and robustness (to missing information) of the proposed particle learning algorithms. The results indicate that the proposed algorithm shows fast convergence rates, yields efficient estimates of the influence matrix, is scalable, and is robust to incomplete information. Further, the network topology, and not just the network size, impacts the learning rate. The learning rate also slows down as the percentage of missing information increases.",
keywords = "Influence estimation, Learning, Opinion dynamics, Particle filter, Social networks",
author = "Castro, {Luis E.} and Shaikh, {Nazrul I}",
year = "2018",
month = "10",
day = "1",
doi = "10.1016/j.csda.2018.01.008",
language = "English (US)",
volume = "126",
pages = "1--18",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

TY - JOUR

T1 - A particle-learning-based approach to estimate the influence matrix of online social networks

AU - Castro, Luis E.

AU - Shaikh, Nazrul I

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Knowing the extent of influence an agent exerts over the other agents over online social networks such as Twitter and Facebook is important as it helps identify opinion leaders and predict how opinions are likely to evolve. However, this information regarding the extent of influence exerted by agents on each other is difficult to obtain as it is unobservable and the data available to estimate it is scarce, often incomplete, and noisy. Further, the number of unknown parameters that need to be estimated to infer the extent of influence between any given pair of agents is very large. A particle-learning-based algorithm is proposed to estimate the influence matrix that indicates the extent of influence any agent exerts on any other in a social network. Computational studies have been used to determine the efficiency, learning rates and asymptotic properties, and robustness (to missing information) of the proposed particle learning algorithms. The results indicate that the proposed algorithm shows fast convergence rates, yields efficient estimates of the influence matrix, is scalable, and is robust to incomplete information. Further, the network topology, and not just the network size, impacts the learning rate. The learning rate also slows down as the percentage of missing information increases.

AB - Knowing the extent of influence an agent exerts over the other agents over online social networks such as Twitter and Facebook is important as it helps identify opinion leaders and predict how opinions are likely to evolve. However, this information regarding the extent of influence exerted by agents on each other is difficult to obtain as it is unobservable and the data available to estimate it is scarce, often incomplete, and noisy. Further, the number of unknown parameters that need to be estimated to infer the extent of influence between any given pair of agents is very large. A particle-learning-based algorithm is proposed to estimate the influence matrix that indicates the extent of influence any agent exerts on any other in a social network. Computational studies have been used to determine the efficiency, learning rates and asymptotic properties, and robustness (to missing information) of the proposed particle learning algorithms. The results indicate that the proposed algorithm shows fast convergence rates, yields efficient estimates of the influence matrix, is scalable, and is robust to incomplete information. Further, the network topology, and not just the network size, impacts the learning rate. The learning rate also slows down as the percentage of missing information increases.

KW - Influence estimation

KW - Learning

KW - Opinion dynamics

KW - Particle filter

KW - Social networks

UR - http://www.scopus.com/inward/record.url?scp=85046630239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046630239&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2018.01.008

DO - 10.1016/j.csda.2018.01.008

M3 - Article

VL - 126

SP - 1

EP - 18

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -