Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quantifying Influencer Impact on Affective Polarization

Rezaur Rashid, Joshua Melton, Ouldouz Ghorbani, Siddharth Krishnan, Shannon Reid, Gabriel Terejanu

TL;DR

This study explores how discussions led by influencers on Twitter, now known as 'X', affect public sentiment and contribute to online polarization, using a counterfactual framework to analyze the polarization scores of conversations in scenarios both with and without the presence of an influential figure.

Abstract

In today's digital age, social media platforms play a crucial role in shaping public opinion. This study explores how discussions led by influencers on Twitter, now known as 'X', affect public sentiment and contribute to online polarization. We developed a counterfactual framework to analyze the polarization scores of conversations in scenarios both with and without the presence of an influential figure. Two case studies, centered on the polarizing issues of climate change and gun control, were examined. Our research highlights the significant impact these figures have on public discourse, providing valuable insights into how online discussions can influence societal divisions.

Quantifying Influencer Impact on Affective Polarization

TL;DR

This study explores how discussions led by influencers on Twitter, now known as 'X', affect public sentiment and contribute to online polarization, using a counterfactual framework to analyze the polarization scores of conversations in scenarios both with and without the presence of an influential figure.

Abstract

In today's digital age, social media platforms play a crucial role in shaping public opinion. This study explores how discussions led by influencers on Twitter, now known as 'X', affect public sentiment and contribute to online polarization. We developed a counterfactual framework to analyze the polarization scores of conversations in scenarios both with and without the presence of an influential figure. Two case studies, centered on the polarizing issues of climate change and gun control, were examined. Our research highlights the significant impact these figures have on public discourse, providing valuable insights into how online discussions can influence societal divisions.
Paper Structure (18 sections, 4 figures, 7 tables)

This paper contains 18 sections, 4 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Data
  5. Data Collection
  6. Data Exploration
  7. Influential Users
  8. Quantifying Polarization with E/I Index
  9. User Stance Labeling using Graph Neural Networks (GNNs)
  10. Initial Label Generation
  11. Expanding Stance Labeling with GNNs
  12. Optimization of Classification Thresholds
  13. Approach to Quantifying Influencer Impact on Affective Polarization
  14. Results
  15. Effect of an Influential-led Conversation
  16. ...and 3 more sections

Figures (4)

  • Figure 1: Interaction networks with and without a specific conversation. The left panel displays the network including the conversation (circled), while the right panel shows the network without it, highlighting the dense areas where ongoing interactions among the influencer's followers persist through other conversations.
  • Figure 2: Conversation characteristics: (a) Gun Control and (b) Climate Change topics, displaying the frequency of conversations by number of tweets (left) and number of users (right).
  • Figure 3: Daily conversation counts over the specified time frame, stratified by topic: (a) Gun Control and (b) Climate Change.
  • Figure 4: Temporal dynamics of polarization scores in response to events. The top trio of subfigures (a-c) illustrates changes in polarization preceding and following events related to gun control, with '(P $\rightarrow$ A)' denoting shifts from pro-to-anti gun control stance and '(A $\rightarrow$ P)' denoting shifts from anti-to-pro stance. The bottom trio (d-f) depicts similar changes for climate change-related events, with '(B $\rightarrow$ D)' representing shifts from believe-to-disbelieve in climate change and '(D $\rightarrow$ B)' for shifts from disbelieve-to-believe stance direction. P-values indicate the statistical significance of changes, confirming that these shifts are not random but are influenced by the events.