Accepted for/Published in: JMIR Public Health and Surveillance
Date Submitted: Sep 25, 2020
Date Accepted: Jan 15, 2021
Date Submitted to PubMed: Jan 22, 2021
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Comparing News and Tweets about COVID-19 in Brazil
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 Internet.
Objective:
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 Internet.
Methods:
This work proposes a methodology based on topic modeling, named entity recognition and sentiment analysis of the text to compare Twitter posts and news, followed by 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 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.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.