A hybrid epidemic model for deindividuation and antinormative behavior in online social networks

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

With the increasing popularity of user-contributed sites, the phenomenon of “social pollution”, the presence of abusive posts has become increasingly prevalent. In this paper, we describe a novel approach to investigate negative behavior dynamics in online social networks as epidemic phenomena. We show that using hybrid automata, it is possible to explain the contagion of antinormative behavior in certain online commentaries. We present two variations of a finite-state machine model for time-varying epidemic dynamics, namely triggered state transition and iterative local regression, which differ with respect to accuracy and complexity.We validate the model with experiments over a dataset of 400,000 comments on 800 YouTube videos, classified by genre, and indicate how different epidemic patterns of behavior can be tied to specific interaction patterns among users.

Original languageEnglish (US)
Article number13
JournalSocial Network Analysis and Mining
Volume6
Issue number1
DOIs
StatePublished - Dec 1 2016

Fingerprint

social network
Finite automata
Pollution
interaction pattern
popularity
genre
video
Experiments
regression
experiment

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Communication
  • Media Technology
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

@article{2097edd4e8c842e8afbe70feb7c8d86a,
title = "A hybrid epidemic model for deindividuation and antinormative behavior in online social networks",
abstract = "With the increasing popularity of user-contributed sites, the phenomenon of “social pollution”, the presence of abusive posts has become increasingly prevalent. In this paper, we describe a novel approach to investigate negative behavior dynamics in online social networks as epidemic phenomena. We show that using hybrid automata, it is possible to explain the contagion of antinormative behavior in certain online commentaries. We present two variations of a finite-state machine model for time-varying epidemic dynamics, namely triggered state transition and iterative local regression, which differ with respect to accuracy and complexity.We validate the model with experiments over a dataset of 400,000 comments on 800 YouTube videos, classified by genre, and indicate how different epidemic patterns of behavior can be tied to specific interaction patterns among users.",
author = "Cong Liao and Anna Squicciarini and Christopher Griffin and Sarah Rajtmajer",
year = "2016",
month = "12",
day = "1",
doi = "10.1007/s13278-016-0321-5",
language = "English (US)",
volume = "6",
journal = "Social Network Analysis and Mining",
issn = "1869-5450",
publisher = "Springer Wien",
number = "1",

}

TY - JOUR

T1 - A hybrid epidemic model for deindividuation and antinormative behavior in online social networks

AU - Liao, Cong

AU - Squicciarini, Anna

AU - Griffin, Christopher

AU - Rajtmajer, Sarah

PY - 2016/12/1

Y1 - 2016/12/1

N2 - With the increasing popularity of user-contributed sites, the phenomenon of “social pollution”, the presence of abusive posts has become increasingly prevalent. In this paper, we describe a novel approach to investigate negative behavior dynamics in online social networks as epidemic phenomena. We show that using hybrid automata, it is possible to explain the contagion of antinormative behavior in certain online commentaries. We present two variations of a finite-state machine model for time-varying epidemic dynamics, namely triggered state transition and iterative local regression, which differ with respect to accuracy and complexity.We validate the model with experiments over a dataset of 400,000 comments on 800 YouTube videos, classified by genre, and indicate how different epidemic patterns of behavior can be tied to specific interaction patterns among users.

AB - With the increasing popularity of user-contributed sites, the phenomenon of “social pollution”, the presence of abusive posts has become increasingly prevalent. In this paper, we describe a novel approach to investigate negative behavior dynamics in online social networks as epidemic phenomena. We show that using hybrid automata, it is possible to explain the contagion of antinormative behavior in certain online commentaries. We present two variations of a finite-state machine model for time-varying epidemic dynamics, namely triggered state transition and iterative local regression, which differ with respect to accuracy and complexity.We validate the model with experiments over a dataset of 400,000 comments on 800 YouTube videos, classified by genre, and indicate how different epidemic patterns of behavior can be tied to specific interaction patterns among users.

UR - http://www.scopus.com/inward/record.url?scp=84962532668&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962532668&partnerID=8YFLogxK

U2 - 10.1007/s13278-016-0321-5

DO - 10.1007/s13278-016-0321-5

M3 - Article

AN - SCOPUS:84962532668

VL - 6

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

SN - 1869-5450

IS - 1

M1 - 13

ER -