Measuring the co-evolution of online engagement with (mis)information and its visibility at scale

2025-06-06

AI Summary

This study investigates the co-evolutionary dynamics between user engagement (e.g., retweeting) with (mis)information and source visibility (e.g., follower growth) during major events such as the COVID-19 pandemic. Leveraging over 100 million pandemic-related tweets, we develop a scalable temporal network model integrating large-scale behavioral statistics with event-driven dynamic association mining. We uncover, for the first time, an asymmetric temporal coupling: highly credible sources experience explosive visibility growth early in crises, whereas low-credibility sources exhibit faster baseline growth during normal periods. Based on this, we propose the “engagement–visibility” co-evolution paradigm—a novel framework for modeling attention competition. Validated empirically over three years, the paradigm generalizes to other attention-sensitive domains, including climate change and political discourse.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Computational social science
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Online attention is an increasingly valuable resource in the digital age, with extraordinary events such as the COVID-19 pandemic fuelling fierce competition around it. As misinformation pervades online platforms, users seek credible sources, while news outlets compete to attract and retain their attention. Here we measure the co-evolution of online"engagement"with (mis)information and its"visibility", where engagement corresponds to user interactions on social media, and visibility to fluctuations in user follower counts. Using a scalable temporal network modelling framework applied to over 100 million COVID-related retweets spanning 3 years, we find that highly engaged sources experience sharp spikes in follower growth during major events (e.g., vaccine rollouts, epidemic severity), whereas sources with more questionable credibility tend to sustain faster growth outside of these periods. Our framework lends itself to studying other large-scale events where online attention is at stake, such as climate and political debates.

Problem

• Measure co-evolution of engagement and visibility of misinformation online
• Analyze follower growth patterns during major events like COVID-19
• Study online attention dynamics in large-scale events and debates

Innovation

• Scalable temporal network modeling framework
• Analyzes 100M+ COVID-related retweets
• Tracks engagement and visibility dynamics