Topology comparison of Twitter diffusion networks effectively reveals misleading information

Abstract

In recent years, malicious information had an explosive growth in social media, with serious social and political backlashes. Recent important studies, featuring large-scale analyses, have produced deeper knowledge about this phenomenon, showing that disinformation spreads faster, deeper and more broadly than the truth on social media, where bots and echo chambers play an important role in diffusion networks. Following these directions, we explore the possibility of classifying news articles circulating on social media based exclusively on a topological analysis of their diffusion networks. To this aim we collected a large dataset of diffusion networks on Twitter pertaining to news articles published on two distinct classes of sources, namely outlets that convey mainstream, reliable and objective information and those that fabricate and disseminate various kinds of disinformation stories. We carried out an extensive comparison of these networks using several alignmentfree approaches including basic network properties, centrality measures distributions, and network distances. We accordingly evaluated to what extent these network features allow to discriminate between the networks associated to the aforementioned news domains. Our results highlight that the communities of users spreading mainstream rather than disinformation news tend to shape diffusion networks with subtle yet systematic differences. This opens the way to promptly and correctly identifying disinformation on social media by solely inspecting the resulting diffusion networks.

Combining compact news representations generated using DistilBERT and topological features to classify fake news

“…Um estudo [Reis et al 2019] argumenta que features relacionadas à fonte da notícias e ao engajamento gerado na sua propagação são as mais discriminatórias na classificação de FN. Uma proposta de classificação de meios de comunicação propagadores de FN baseada na topologia da rede de propagação é apresentada em [Pierri et al 2020]. Propostas de features representando o contexto social incluem perfis difusores de notícias em redes sociais [Shu et al 019a], comportamento social (e.g.…”

“…Uma nova tendência em processamento de linguagem natural (PLN) é criar modelos através da transferência de aprendizado de representações de linguagens codificadas usando quantidades massivas de dados, tais como BERT (Bidirectional Encoder Representations from Transformers) [Devlin et al 2019]. Outra oportunidade é verificar se a abordagem topológica para verificar veículos de comunicação difusores de FN proposta em [Pierri et al 2020] pode contribuir à classificação de FN independentemente da fonte. O objetivo deste trabalho é experimentar o uso combinado de conteúdo textual da notícia e da topologia das redes de difusão de notícias para a classificação de FN.…”

Investigating Italian disinformation spreading on Twitter in the context of 2019 European elections

“…In accordance with current literature [6,[9][10][11]24] we use a "source-based" approach: we do not verify each news article manually but we assign the disinformation label to all items published on websites labeled as such (the same holds for fact-checking articles).…”

“…Focusing on 2016 US Presidential elections, recent research has shown that false news spread deeper, faster and broader than truth [6], with social bots and echo chambers playing an important role in the diffusion of deceptive information [7,8]. However, it has also been highlighted that disinformation only amounted to a negligible fraction of online news [9][10][11], the majority of which were exposed to and shared by a restricted community of old and conservative leaning people, highly engaged with political news [9][10][11]. In spite of such small volumes, a study suggested that false news (and the alleged interference of Russian trolls) played an important role in the election of Donald Trump [2].…”

“…Differently from [8], satire was excluded from the analysis. Following literature on the subject [3,7,[9][10][11], we used a "source-based" approach, and assumed that all articles published on aforementioned outlets indeed carried deceptive information; nonetheless, we are aware that this might not be always true and reported cases of misinformation on mainstream outlets are not rare [3]. Our analysis was driven by the following research questions: RQ1: What was the reach of disinformation which circulated on Twitter in the run-up to European Parliament elections?…”