Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media

Bohan Jiang, Lu Cheng, Zhen Tan, Ruocheng Guo, Huan Liu

TL;DR

It is observed that individuals with moderate stances are more vulnerable to the influence of PBN compared to those with extreme views, and distinct user behaviors between social media groups with various vaccine stances are revealed.

Abstract

News media has been utilized as a political tool to stray from facts, presenting biased claims without evidence. Amid the COVID-19 pandemic, politically biased news (PBN) has significantly undermined public trust in vaccines, despite strong medical evidence supporting their efficacy. In this paper, we analyze: (i) how inherent vaccine stances subtly influence individuals' selection of news sources and participation in social media discussions; and (ii) the impact of exposure to PBN on users' attitudes toward vaccines. In doing so, we first curate a comprehensive dataset that connects PBN with related social media discourse. Utilizing advanced deep learning and causal inference techniques, we reveal distinct user behaviors between social media groups with various vaccine stances. Moreover, we observe that individuals with moderate stances, particularly the vaccine-hesitant majority, are more vulnerable to the influence of PBN compared to those with extreme views. Our findings provide critical insights to foster this line of research.

Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media

TL;DR

It is observed that individuals with moderate stances are more vulnerable to the influence of PBN compared to those with extreme views, and distinct user behaviors between social media groups with various vaccine stances are revealed.

Abstract

News media has been utilized as a political tool to stray from facts, presenting biased claims without evidence. Amid the COVID-19 pandemic, politically biased news (PBN) has significantly undermined public trust in vaccines, despite strong medical evidence supporting their efficacy. In this paper, we analyze: (i) how inherent vaccine stances subtly influence individuals' selection of news sources and participation in social media discussions; and (ii) the impact of exposure to PBN on users' attitudes toward vaccines. In doing so, we first curate a comprehensive dataset that connects PBN with related social media discourse. Utilizing advanced deep learning and causal inference techniques, we reveal distinct user behaviors between social media groups with various vaccine stances. Moreover, we observe that individuals with moderate stances, particularly the vaccine-hesitant majority, are more vulnerable to the influence of PBN compared to those with extreme views. Our findings provide critical insights to foster this line of research.
Paper Structure (21 sections, 3 equations, 6 figures, 3 tables)

This paper contains 21 sections, 3 equations, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Political Bias in News Media
  4. COVID-19 Vaccine Stance
  5. Causal Analysis of COVID-Related Factors
  6. Bridging News Media and Social Media
  7. Data Collection
  8. PBN from Allsides.
  9. Social Media Data from Twitter.
  10. Data Annotation
  11. Data Selection
  12. RQ1. Behavior Analysis of Three Vaccine Stance Groups
  13. Vaccine Stance Groups.
  14. News Consumption Behavior.
  15. Sociel Media Discussion.
  16. ...and 6 more sections

Figures (6)

  • Figure 1: An overview of our research pipeline. On the left, it depicts news outlets disseminating COVID-related PBN to wide audiences via social media platforms. The right side illustrates the potential influence of such PBN exposure on users' vaccine stances. We define exposure as instances where a user engages with PBN through Retweets or Quote-tweets (Retweets with added comments). Discussion refers to user involvement in vaccine-related conversations after PBN exposure. Change denotes the variation in users' vaccine stances resulting from PBN exposure.
  • Figure 2: An example of the data collection process. We first collect a set of COVID-related news triplets containing articles from left-leaning, center-leaning, and right-leaning outlets from Allsides (top). We then obtain associated Twitter data (bottom).
  • Figure 3: Ratio of left-, right-, and center-leaning news media of pro-vaccine, anti-vaccine, and vaccine-hesitant groups.
  • Figure 4: Overall (a) and monthly (b) percentage of Twitter discussions associated with five COVID-vaccine-related topics among the pro-vaccine group, anti-vaccine group, and vaccine-hesitant group.
  • Figure 5: Two causal DAG of our studied problem. The left one (a) assumes all confounding variables are observed. The right one (b) uses proxies to approximate latent confounders.
  • ...and 1 more figures