Detection of Misinformation about COVID-19 in Brazilian Portuguese WhatsApp Messages Using Deep Learning

Abstract

During the COVID-19 pandemic, the misinformation problem arose once again through social networks, like a harmful health advice and false solutions epidemic. In Brazil, as well as in many developing countries, one of the primary sources of misinformation is the messaging application WhatsApp. Thus, the automatic misinformation detection (MID) about COVID-19 in Brazilian Portuguese WhatsApp messages becomes a crucial challenge. Still, due to WhatsApp's private messaging nature, there are still few methods of misinformation detection developed specifically for the WhatsApp platform. In this paper, we propose a new approach, called MIDeepBR, based on BiLSTM neural networks, pooling operations and attention mechanism, which is able to automatically detect misinformation in Brazilian Portuguese WhatsApp messages. Experimental results evidence the suitability of the proposed approach to automatic misinformation detection. Our best results achieved an F1 score of 0.834, while in previous works, the best results achieved an F1 score of 0.778. Thus, MIDeepBR outperforms the previous works.

Illusion of Truth: Analysing and Classifying COVID-19 Fake News in Brazilian Portuguese Language

“…More recently, the Digital Lighthouse project at the Universidade Federal do Ceara in Brazil has published a number of studies and datasets relating to misinformation on WhatsApp in Brazil. These include FakeWhatsApp.BR [91] and COVID19.BR [92,93]. The FakeWhatsApp.BR dataset contains 282,601 WhatsApp messages from users and groups from all Brazilian states collected from 59 groups from July 2018 to November of 2018 [91].…”

“…The corpus contains 2043 messages, 865 labelled as misinformation and 1178 labelled as non-misinformation. Both datasets contain similar data, i.e., message text, time and date, phone number, Brazilian state, word count, character count and whether the message contained media [91,93]. Cabral et al [91] combined classic natural language processing approaches for feature extraction with nine different machine learning classification algorithms to detect fake news on WhatsApp, i.e., logistic regression, Bernoulli, complement naive Bayes, SVM with a linear kernel (LSVM), SVM trained with stochastic gradient descent (SGD), SVM trained with an RBF kernel, K-nearest neighbours, Random Forest (RF), gradient boosting and a multilayer perceptron neural network (MLP).…”

“…Here, they achieved a highest F1 score of 0.778; an analysis of errors indicated errors occurred primarily due to short message length. In Martins et al [93], they extend their work to detect COVID-19 misinformation in Brazilian Portuguese WhatsApp messages using bidirectional long-short term memory (BiLSTM) neural networks, pooling operations and an attention mechanism. This solution, called MIDeepBR, outperformed their previous proposal as reported in [92] with an F1 score of 0.834.…”

“…In contrast with Martins et al [92] and Cabral et al [91], we do not use a WhatsApp dataset, which may due to its nature be dominated by L-variant Brazilian Portuguese. Furthermore, the dataset used in this study is over a longer period (12 months) compared with Martins et al [92,93] and Cabral et al [91]. Furthermore, unlike Li et al [81], we specifically focus on the Brazilian Portuguese language as distinct from European or African variants.…”

Detecção Automática de Desinformação Relacionada à Covid-19 no Brasil

“…Essas duas bases de dados são mais gerais, não possuindo foco em algum tema específico. Mais relacionado ao contexto do nosso trabalho, no estudo de Martins et al foi apresentado o COVID-19.BR, uma base de dados manualmente rotulada contendo mensagens do What-sApp sobre o Covid-19 escritas no idioma Português [Martins et al 2021]. No entanto, diferentemente dos esforc ¸os anteriores, estamos focados em desinformac ¸ão disseminada por veículos de baixa credibilidade.…”