Controlling the Misinformation Diffusion in Social Media by the Effect of Different Classes of Agents

TL;DR

Addressing misinformation diffusion on social networks, the paper develops an ABM framework that extends the SBFC model with four agent classes represented by states $S$, $B$, and $FC$, with transitions $f_i^B(t)$ and $f_i^{FC}(t)$ driven by parameters $\alpha$, $\beta$, $p_f$, and $p_v$. It applies this framework to a real Facebook network, clustering nodes into communities and assigning roles to scholars, influencers, normal users, and bots to reflect heterogeneity in verification and forgetting behavior. The authors propose two interventions—educating scholars/influencers to improve verification and deploying fact-checker bots to spread facts—and show that both strategies reduce misinformation spread, with the strongest control when combined and supported by larger scholar communities. The findings offer practical guidance for misinformation containment, demonstrating that targeted education and strategic bot deployment can shift the network toward fact-checking dominance, and they provide a replicable NetLogo framework for further exploration of diffusion dynamics in real-world networks.

Abstract

The rapid and widespread dissemination of misinformation through social networks is a growing concern in today's digital age. This study focused on modeling fake news diffusion, discovering the spreading dynamics, and designing control strategies. A common approach for modeling the misinformation dynamics is SIR-based models. Our approach is an extension of a model called 'SBFC' which is a SIR-based model. This model has three states, Susceptible, Believer, and Fact-Checker. The dynamics and transition between states are based on neighbors' beliefs, hoax credibility, spreading rate, probability of verifying the news, and probability of forgetting the current state. Our contribution is to push this model to real social networks by considering different classes of agents with their characteristics. We proposed two main strategies for confronting misinformation diffusion. First, we can educate a minor class, like scholars or influencers, to improve their ability to verify the news or remember their state longer. The second strategy is adding fact-checker bots to the network to spread the facts and influence their neighbors' states. Our result shows that both of these approaches can effectively control the misinformation spread.

Figures (7)

• Figure 1: dynamics of SBFC model tambuscio2015fact.
• Figure 2: Facebook network with 8 clusters labeled by different colors.
• Figure 3: Standard deviation for each state, based on the replicates.
• Figure 4: Difference between each input value related to spreading dynamics on final agents' count for each state. The first two columns from left are for Believers (B), the next two are for Fact-checkers (F), and the last two are for Susceptibles (S)
• Figure 5: The effect of scholars' community size on the states of agents. ($\alpha = 0.8$, $p_{verify-scholars} = 0.3$, and $p_{forget-scholar} = 0.02$)