Analyzing the Impact of COVID-19 on Portuguese Social Media

The COVID-19 pandemic has had a widespread global impact, with social media platforms such as Twitter serving as a key source of communication and information sharing. In this study, we present the first large-scale Portuguese Twitter dataset on COVID-19, providing a unique perspective on the impact of the pandemic on Portuguese-speaking communities on social media. The dataset includes over 31 million Tweets from 2020 and 2021. We conducted sentiment analysis using the LeIA (Lexicon for Adapted Inference) model to examine the relationship between spikes in Tweet count and sentiment scores with news articles and government announcements in Portugal and Brazil. Additionally, we employed manual data clustering, providing more insights into the data and understanding of its composition. We perform a comparative analysis among different groups to understand how the dataset’s composition changes over time and compare this between Portugal and Brazil. This research offers valuable insights into the pandemic’s impact on Portuguese-speaking communities on social media. The dataset is available on https://github.com/bioinformatics-ua/Portuguese-Covid19-Dataset .