🤖 AI Summary
This study addresses the lack of individual psychological dynamics in modeling health misinformation propagation on social media by proposing the ELM-SIRMMM framework. This approach integrates psychological signals, including emotion and engagement from the Elaboration Likelihood Model (ELM), into a six-compartment epidemiological model to enable behavior-driven dynamic modulation of transmission rates. Multi-dataset validation demonstrates that the framework significantly enhances prediction accuracy and dynamic realism. Specifically, on the FibVID dataset, it reduces RMSE by 5.5% and corrects peak timing by 10 days. Furthermore, on MC-Fake, it accurately reproduces flash-rumor patterns with a 97% recovery rate, confirming the critical role of psychological mechanisms in achieving precise misinformation propagation modeling.
📝 Abstract
This study presents a hybrid epidemiological and behavioural framework to simulate the spread of health misinformation on social media. We extend the classical Susceptible--Infected--Recovered (SIR) model to a six-compartment structure (SIRMMM), incorporating Misinformed Susceptible (MS), Misinformed Infected (MI), and Misinformed Recovered (MR) compartments to better reflect the dynamics of the misinformation lifecycle. To account for individual-level behavioural variation, we extend the SIRMMM model by integrating psychological signals from the Elaboration Likelihood Model (ELM), including sentiment polarity, engagement metrics, and cognitive effort, which dynamically modulate the misinformation transmission rate, yielding the ELM-SIRMMM framework. Model parameters were estimated using the FibVID dataset, which captures COVID-19 misinformation on Twitter. Generalisability was tested on two additional datasets: MC-Fake (emotional misinformation) and Monant (general health misinformation). Results show that the ELM-SIRMMM model enhances both predictive accuracy and dynamic realism. On FibVID, it decreases RMSE by 5.5%, delays the misinformation peak from day 150 to day 160, and increases its peak prevalence from 6% to 7%. On MC-Fake, it accurately reproduces a flash-rumour pattern, infecting 38% of users by day 45 and achieving 97% misinformation recovery, all while maintaining model accuracy. In contrast, minimal behavioural signal variability in the Monant dataset leads to marginal benefit, with only a 3% peak and 57% of users remaining susceptible. These findings suggest that structural elaboration alone is insufficient. Functional realism in modelling misinformation spread requires dynamic psychological inputs that vary meaningfully across time and contexts.