Using Python to detect fake news about covid-19: challenges and possibilities

This work aims to report strategies for collecting a dataset in Portuguese for training Artificial Intelligence models to automatically identify fake news about covid-19 disseminated during the pandemic, using Python code. We analyze a fake news detection method based on a Recurrent Neural Network a...

ver descrição completa

Detalhes bibliográficos
Autores: Ferreira, Fernanda Vasques, Varão, Rafiza, Boselli, Marco Aurélio, Santos, Leandro Brito, Moret, Marcelo A.
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2022
País:Brasil
Recursos:Fundação Oswaldo Cruz (FIOCRUZ)
Repositório:RECIIS (Online)
Idioma:português
OAI Identifier:oai:www.reciis.icict.fiocruz.br:article/3253
Acesso em linha:https://www.reciis.icict.fiocruz.br/index.php/reciis/article/view/3253
Access Level:Acceso aberto
Palavra-chave:Fake news
Artificial Intelligence
Covid-19
Python
Misinformation.
Noticias falsas
Inteligencia artificial
Desinformación.
Inteligência artificial
Desinformação.
Descrição
Resumo:This work aims to report strategies for collecting a dataset in Portuguese for training Artificial Intelligence models to automatically identify fake news about covid-19 disseminated during the pandemic, using Python code. We analyze a fake news detection method based on a Recurrent Neural Network and supervised learning. We selected a corpus with 7,200 texts collected on websites and news agencies by Monteiro et al. (2018), each one of them previously cataloged as true or false as a training and validation dataset. This model was used to detect fake news about covid-19 in a set of news collected and classified by the authors of this work. The hit rate was 70%.