|
?:abstract
|
-
BACKGROUND COVID-19 pandemic is severely affecting people all over the world. Nowadays, an important approach to understand such a phenomenon and its impacts on the lives of people consists of monitoring social networks and news on the Internet. OBJECTIVE The purpose of this study is to present a methodology to capture the main subjects and themes under discussion by news and social media, and to apply it to analyse the COVID-19 pandemic in Brazil. METHODS This work proposes a methodology based on topic modeling, named entity recognition and sentiment analysis of texts to compare Twitter posts and news, followed by an envision of COVID evolution and impacts. We have focused on an analysis in Brazil, one important epicenter of the pandemic in the world, so we have faced the challenge to deal with Brazilian Portuguese texts. RESULTS This work collected and analysed 18,413 articles from news media, and 1,597,934 tweets posted by 1,299,084 users in Brazil. Results show that the proposed methodology improved the topic-sentiment analysis over time, so a better monitoring of Internet media is allowed. Besides, with this tool, we extracted some interesting insights about COVID evolution in Brazil. For instance, we found out that Twitter presents similar topic coverage from news media, the main entities are similar, but they differ in theme distribution and entity diversity. Besides, some aspects represent a negative sentiment of political theme from both media, and a high incidence of mentions to a specific drug denotes a high political polarization of the pandemic. CONCLUSIONS This study identified the main themes under discussion in both news and social media and how their sentiment evolved over time. It is possible to understand what are the major public\'s concerns during the pandemic, and so all the obtained information are useful for decision making by the authorities.
|
![[This page as RDF]](https://research.tib.eu/covid-19/static/rdf-icon.gif){kind=icon}