The Ripple Effect: Modeling the Spread and Containment of Harmful Content Across Interconnected Communities

Gatta et al. (2023) highlight the cross-platform spread of harmful content, but current models rarely integrate the structure and dynamics of interconnected communities (see also Lee et al., 2020 for health contexts). By leveraging MADOC and drawing on network science and epidemiology, this research would model the “infection” and containment of harmful posts, considering factors like user migration, moderation interventions, and community overlap. What conditions accelerate or dampen the spread? How do “bridge” users influence outcomes? Can targeted interventions in one community stifle a cascade? The novelty is in combining real cross-platform data with sophisticated diffusion models, with practical significance for coordinated moderation, public health, and information integrity.

References:

1. Multi-Platform Aggregated Dataset of Online Communities (MADOC). Marija Mitrovic, Aleksandar Tomašević, S. Maletić, Miroslav Andjelković, Anja Vranic, Darja Cvetković, Boris Stupovski, Dusan Vudragovic, Sara Major, Aleksandar Bogojevi'c (2025). International Conference on Web and Social Media.
2. Link Predictions in an Online Health Community for Smoking Cessation. Sulyun Lee, Hankyu Jang, K. Zhao, Michael S. Amato, Amanda L. Graham (2020).
3. Multi-Platform Aggregated Dataset of Online Communities (MADOC). Marija Mitrovic, Aleksandar Tomašević, S. Maletić, Miroslav Andjelković, Anja Vranic, Darja Cvetković, Boris Stupovski, Dusan Vudragovic, Sara Major, Aleksandar Bogojevi'c (2025). International Conference on Web and Social Media.
4. The Interconnected Nature of Online Harm and Moderation: Investigating the Cross-Platform Spread of Harmful Content between YouTube and Twitter. V. Gatta, Luca Luceri, Francesco Fabbri, Emilio Ferrara (2023). ACM Conference on Hypertext & Social Media.