Abstract
Mitigating misinformation on social media is an unresolved challenge, particularly because of the complexity of information dissemination. To this end, Multivariate Hawkes Processes (MHP) have become a fundamental tool because they model social network dynamics, which facilitates execution and evaluation of mitigation policies. In this paper, we propose a novel light-weight intervention-based misinformation mitigation framework using decentralized Learning Automata (LA) to control the MHP. Each automaton is associated with a single user and learns to what degree that user should be involved in the mitigation strategy by interacting with a corresponding MHP, and performing a joint random walk over the state space. We use three Twitter datasets to evaluate our approach, one of them being a new COVID-19 dataset provided in this paper. Our approach shows fast convergence and increased valid information exposure. These results persisted independently of network structure, including networks with central nodes, where the latter could be the root of misinformation. Further, the LA obtained these results in a decentralized manner, facilitating distributed deployment in real-life scenarios.
Highlights
The spread of misinformation on social media can have critical consequences during a crisis
If we look at a point process on the non-negative real numbers line, where the latter is representing the time, the point process is a random process whose realizations r consist of the event times stages {t0, t1, ... tr } and they define the time by when an event has occurred
We propose a novel exercise of the Learning Automata (LA) in the domain of social media misinformation mitigation
Summary
The spread of misinformation on social media can have critical consequences during a crisis. Whether the crisis is a disaster, political struggle, terrorist attack, natural hazard, or a pandemic, misleading information such as rumors and false alarm can impede or endanger a successful outcome, such as effective response to a natural hazard. According to a recent study (Bradshaw and Howard 2017), at least. 50% of the world’s countries suffer from organized political manipulation campaigns over social media. Other examples of the damaging effect of misinformation circulated over social media includes the Ebola outbreak in West Africa (Jin et al 2014), which was believed to be three times more worse than the previous Ebola outbreaks. With a more connected world, the impact of misinformation is getting more severe, even becoming a global threat. There is an increasing interest among researchers, and society in general, in finding solutions for combating misinformation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
