Social Networks Analysis

Information disorders during the COVID-19 infodemic: The case of Italian Facebook

The recent COVID-19 pandemic came alongside with an “infodemic”, with online social media flooded by often unreliable information associating the medical emergency with popular subjects of disinformation. In Italy, one of the first European countries suffering a rise in new cases and dealing with a total lockdown, controversial topics such as migrant flows and the 5G technology were often associated online with the origin and diffusion of the virus. In this work we analyze COVID-19 related conversations on the Italian Facebook, collecting over 1.5M posts shared by nearly 80k public pages and groups for a period of four months since January 2020. On the one hand, our findings suggest that well-known unreliable sources had a limited exposure, and that discussions over controversial topics did not spark a comparable engagement with respect to institutional and scientific communication. On the other hand, however, we realize that dis- and counter-information induced a polarization of (clusters of) groups and pages, wherein conversations were characterized by a topical lexicon, by a great diffusion of user generated content, and by link-sharing patterns that seem ascribable to coordinated propaganda. As revealed by the URL-sharing diffusion network showing a “small-world” effect, users were easily exposed to harmful propaganda as well as to verified information on the virus, exalting the role of public figures and mainstream media, as well as of Facebook groups, in shaping the public opinion. (Paper)

Characterizing networks of propaganda on twitter: a case study

The daily exposure of social media users to propaganda and disinformation campaigns has reinvigorated the need to investigate the local and global patterns of diffusion of different (mis)information content on social media. Echo chambers and influencers are often deemed responsible of both the polarization of users in online social networks and the success of propaganda and disinformation campaigns. This article adopts a data-driven approach to investigate the structuration of communities and propaganda networks on Twitter in order to assess the correctness of these imputations. In particular, the work aims at characterizing networks of propaganda extracted from a Twitter dataset by combining the information gained by three different classification approaches, focused respectively on (i) using Tweets content to infer the “polarization” of users around a specific topic, (ii) identifying users having an active role in the diffusion of different propaganda and disinformation items, and (iii) analyzing social ties to identify topological clusters and users playing a “central” role in the network. The work identifies highly partisan community structures along political alignments; furthermore, centrality metrics proved to be very informative to detect the most active users in the network and to distinguish users playing different roles; finally, polarization and clustering structure of the retweet graphs provided useful insights about relevant properties of users exposure, interactions, and participation to different propaganda items. (Paper)

Beyond fact-checking: Network analysis tools for monitoring disinformation in social media

Operated by the H2020 SOMA Project, the recently established Social Observatory for Disinformation and Social Media Analysis supports researchers, journalists and fact-checkers in their quest for quality information. At the core of the Observatory lies the DisInfoNet Toolbox, designed to help a wide spectrum of users understand the dynamics of (fake) news dissemination in social networks. DisInfoNet combines text mining and classification with graph analysis and visualization to offer a comprehensive and user-friendly suite. To demonstrate the potential of our Toolbox, we consider a Twitter dataset of more than 1.3M tweets focused on the Italian 2016 constitutional referendum and use DisInfoNet to: (i) track relevant news stories and reconstruct their prevalence over time and space; (ii) detect central debating communities and capture their distinctive polarization/narrative; (iii) identify influencers both globally and in specific “disinformation networks”.(Paper)