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

Research output: Contribution to journalArticle

4 Scopus citations

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

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'A hybrid epidemic model for deindividuation and antinormative behavior in online social networks'. Together they form a unique fingerprint.

Cite this