Cutting through the noise to motivate people: A comprehensive analysis of COVID-19 social media posts de/motivating vaccination

TL;DR

Problem: COVID-19 vaccination decisions are shaped by misinformation and social-media discourse. Approach: a two-year Twitter analysis using DistilBERT for de/motivation classification, ct-BERT for stance, and BERTopic for topic discovery, across time, geography, and political context. Contributions: a labeled Twitter dataset with motivation and stance, robust classifiers, topic models for motivating/demotivating themes, and reproducible resources. Findings: motivating topics are stable across time and location, while demotivating topics shift with politics; intrinsic motivation and trust in science are more effective at promoting vaccination; local political dynamics influence stances. Impact: insights support targeted, intrinsically motivated public-health messaging and reveal where political framing undermines vaccine uptake, with publicly released datasets and models enabling future work.

Abstract

The COVID-19 pandemic exposed significant weaknesses in the healthcare information system. The overwhelming volume of misinformation on social media and other socioeconomic factors created extraordinary challenges to motivate people to take proper precautions and get vaccinated. In this context, our work explored a novel direction by analyzing an extensive dataset collected over two years, identifying the topics de/motivating the public about COVID-19 vaccination. We analyzed these topics based on time, geographic location, and political orientation. We noticed that while the motivating topics remain the same over time and geographic location, the demotivating topics change rapidly. We also identified that intrinsic motivation, rather than external mandate, is more advantageous to inspire the public. This study addresses scientific communication and public motivation in social media. It can help public health officials, policymakers, and social media platforms develop more effective messaging strategies to cut through the noise of misinformation and educate the public about scientific findings.

Figures (13)

• Figure 1: Preparing the datasets with COVID-19 related tweets.
• Figure 2: Number of tweets in different states (not showing Alaska, Hawaii, and distant territories).
• Figure 3: Classification of tweets and identifying the topics and stance.
• Figure 4: Hierarchy of topics related to vaccine in motivating tweets.
• Figure 5: Top 10 topics in motivating tweets and their spread in the top 15 (by the number of tweets) US states.