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...

Descripción completa

Detalles Bibliográficos
Autores: Ferreira, Fernanda Vasques, Varão, Rafiza, Boselli, Marco Aurélio, Santos, Leandro Brito, Moret, Marcelo A.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:Brasil
Institución:Fundação Oswaldo Cruz (FIOCRUZ)
Repositorio:RECIIS (Online)
Idioma:portugués
OAI Identifier:oai:www.reciis.icict.fiocruz.br:article/3253
Acceso en línea:https://www.reciis.icict.fiocruz.br/index.php/reciis/article/view/3253
Access Level:acceso abierto
Palabra clave:Fake news
Artificial Intelligence
Covid-19
Python
Misinformation.
Noticias falsas
Inteligencia artificial
Desinformación.
Inteligência artificial
Desinformação.
Descripción
Sumario: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%.