Topic detection and sentiment analysis in Twitter content related to COVID-19 from Brazil and the USA.

Twitter is a social media platform with more than 500 million users worldwide. It has become a tool for spreading the news, discussing ideas and comments on world events. Twitter is also an important source of health-related information, given the amount of news, opinions and information that is shared by both citizens and official sources. It is a challenge identifying interesting and useful content from large text-streams in different languages, few works have explored languages other than English. In this paper, we use topic identification and sentiment analysis to explore a large number of tweets in both countries with a high number of spreading and deaths by COVID-19, Brazil, and the USA. We employ 3,332,565 tweets in English and 3,155,277 tweets in Portuguese to compare and discuss the effectiveness of topic identification and sentiment analysis in both languages. We ranked ten topics and analyzed the content discussed on Twitter for four months providing an assessment of the discourse evolution over time. The topics we identified were representative of the news outlets during April and August in both countries. We contribute to the study of the Portuguese language, to the analysis of sentiment trends over a long period and their relation to announced news, and the comparison of the human behavior in two different geographical locations affected by this pandemic. It is important to understand public reactions, information dissemination and consensus building in all major forms, including social media in different countries. • We compared topic modeling for English and Portuguese tweets related to COVID-19. • The topics we identified were representative from the news from April to August. • We ranked ten topics for both languages and notice most of them are similar. • We performed sentiment analysis and negative emotions were dominant in the pandemic. • For sentiment analysis we compare several classifiers and features (n-grams and embeddings). [ABSTRACT FROM AUTHOR]