Câmaras de eco e mis/desinformação sobre vacinas contra a COVID-19 no Twitter: abordagem baseada em machine learning e análise de redes sociais

• Autor(a) principal: Lopes, Arthur da Silva
• Data de Publicação: 2023
• Outros Autores: Brotas, Antonio
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Research, Society and Development
• Texto Completo: https://rsdjournal.org/index.php/rsd/article/view/40159
• topic: Vaccine; Infodemics; Fake News; Echo Chambers; Twitter; Machine learning.; Vacina; Infodemia; Fake News; Câmaras de Eco; Twitter; Machine learning.; Vacuna; Infodemia; Fake News; Cámaras de Eco; Twitter; Machine learning.

Given the infodemiological importance of echo chambers in the dissemination of mis/disinformation, we aimed to analyze the interaction networks of users most exposed to mis/disinformation or controversy about vaccines in the context of the COVID-19 pandemic. To this end, a methodology based on machine learning and Social Network Analysis is proposed in this research for automated detection of controversial and mis/disinformative content about vaccines, through which a model with 92% accuracy was achieved. Out of the nearly 24 million tweets collected, 12.4 million (52%) were flagged as controversial and/or potential for mis/disinformation, and the months of January and June 2021 were those with the highest activity, being analyzed through a cohort. Unlike previous work, we analyzed the network of all ways of interacting on Twitter, and the entire textual structure of the tweets - not just links or hashtags -.  Regarding the conversation about COVID-19 vaccines, the findings were different from those associated with party-political discussion previously described in the literature, since the network of mentions and replies privileges heterophilic relationships, and "echo" conformations were not observable. Finally, further studies are needed to better understand the dissemination of misinformation about vaccines on Twitter.