Influence Cascades: Entropy-Based Characterization of Behavioral Influence Patterns in Social Media

Abstract

Influence cascades are typically analyzed using a single metric approach, i.e., all influence is measured using one number. However, social influence is not monolithic; different users exercise different influences in different ways, and influence is correlated with the user and content-specific attributes. One such attribute could be whether the action is an initiation of a new post, a contribution to a post, or a sharing of an existing post. In this paper, we present a novel method for tracking these influence relationships over time, which we call influence cascades, and present a visualization technique to better understand these cascades. We investigate these influence patterns within and across online social media platforms using empirical data and comparing to a scale-free network as a null model. Our results show that characteristics of influence cascades and patterns of influence are, in fact, affected by the platform and the community of the users.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jan 28, 2021
Source ID
10.3390/e23020160

Entities

People

  • Chathika Gunaratne
  • Chathura Jayalath
  • Chathurani Senevirathna
  • Ivan I Garibay
  • William Rand

Organizations

  • Defense Advanced Research Projects Agency

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.
  • Phased Array Antenna Design.