Mutual Influence of Users Credibility and News Spreading in Online Social Networks

Abstract

A real-time news spreading is now available for everyone, especially thanks to Online Social Networks (OSNs) that easily endorse gate watching, so the collective intelligence and knowledge of dedicated communities are exploited to filter the news flow and to highlight and debate relevant topics. The main drawback is that the responsibility for judging the content and accuracy of information moves from editors and journalists to online information users, with the side effect of the potential growth of fake news. In such a scenario, trustworthiness about information providers cannot be overlooked anymore, rather it more and more helps in discerning real news from fakes. In this paper we evaluate how trustworthiness among OSN users influences the news spreading process. To this purpose, we consider the news spreading as a Susceptible-Infected-Recovered (SIR) process in OSN, adding the contribution credibility of users as a layer on top of OSN. Simulations with both fake and true news spreading on such a multiplex network show that the credibility improves the diffusion of real news while limiting the propagation of fakes. The proposed approach can also be extended to real social networks.

Reducing COVID-19 Misinformation Spread by Introducing Information Diffusion Delay Using Agent-based Modeling

“…It misleads people during health emergencies [27], especially during the COVID-19 pandemic. It has been challenging to track the traveling of COVID-19 misinformation across social networks [28] and to analyze the influenced users and communities over time [29].…”

Towards Digital Twin-Oriented Complex Networked Systems: Introducing heterogeneous node features and interaction rules

“…Current studies generally build CNSs with hybrid components (e.g. real networks and simulated dynamic processes) due to the partial observability of a real-world scenario [ 5 – 11 , 20 , 21 ].…”

“…interactions, relationships, etc.) and their corresponding attributes (which describe the features of nodes and edges), and (ii) dynamic processes that aim to model the spreading phenomena on social networks, such as epidemic spread [2], opinion spread [3], rumour spread [4], news spread [5], etc.…”

Link Prediction in Time Varying Social Networks

“…For instance, in [29], the authors present a survey of the uses of geometric deep learning in Facebook post analysis in order to study the way to preserve the social network integrity, while in [30], the authors present a geometric deep learning-based approach to automatic detection of fake news based on analysis of existing content instead of using Natural Languages Processing techniques that often are not able to manage the context. Another example is to study geometric properties of the propagation scheme, whereby the authors of [31][32][33][34] show that fake and real news spread differently on social media, and Suno et al, in [35], focus on realistic propagation mechanism and highlight the different propagation evolution of fake news and real news tracking large real databases. In fact, online users tend to acquire information adhering to their worldviews [36], ignoring dissenting information [37] that increases the probability of the spreading of misinformation [38], which may cause fake news and inaccurate information to spread faster and wider than fact-based news [39].…”