Combating fake news by empowering fact-checked news spread via topology-based interventions
arXiv:2107.05016
Abstract
Rapid information diffusion and large-scaled information cascades can enable the undesired spread of false information. A small-scaled false information outbreak may potentially lead to an infodemic. We propose a novel information diffusion and intervention technique to combat the spread of false news. As false information is often spreading faster in a social network, the proposed diffusion methodology inhibits the spread of false news by proactively diffusing the fact-checked information. Our methodology mainly relies on defining the potential super-spreaders in a social network based on their centrality metrics. We run an extensive set of experiments on different networks to investigate the impact of centrality metrics on the performance of the proposed diffusion and intervention models. The obtained results demonstrate that empowering the diffusion of fact-checked news combats the spread of false news further and deeper in social networks.
References in corpus (8)
- Community detection in graphs
- Benchmark graphs for testing community detection algorithms
- Assessing the risks of "infodemics" in response to COVID-19 epidemics
- Hoaxy: A Platform for Tracking Online Misinformation
- A first look at COVID-19 information and misinformation sharing on Twitter
- Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs
- Maximizing the Spread of Cascades Using Network Design
- Learning Hierarchical Discourse-level Structure for Fake News Detection