Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation
This article presents a study that applied opinion analysis about COVID-19 immunization in Brazil. An initial set of 143,615 tweets was collected containing 49,477 pro- and 44,643 anti-vaccination and 49,495 neutral posts. Supervised classifiers (multinomial naïve Bayes, logistic regression, linear...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Tropical Medicine and Infectious Disease |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2414-6366/7/10/256 |
| _version_ | 1797469781870247936 |
|---|---|
| author | Victor Diogho Heuer de Carvalho Thyago Celso Cavalcante Nepomuceno Thiago Poleto Jean Gomes Turet Ana Paula Cabral Seixas Costa |
| author_facet | Victor Diogho Heuer de Carvalho Thyago Celso Cavalcante Nepomuceno Thiago Poleto Jean Gomes Turet Ana Paula Cabral Seixas Costa |
| author_sort | Victor Diogho Heuer de Carvalho |
| collection | DOAJ |
| description | This article presents a study that applied opinion analysis about COVID-19 immunization in Brazil. An initial set of 143,615 tweets was collected containing 49,477 pro- and 44,643 anti-vaccination and 49,495 neutral posts. Supervised classifiers (multinomial naïve Bayes, logistic regression, linear support vector machines, random forests, adaptative boosting, and multilayer perceptron) were tested, and multinomial naïve Bayes, which had the best trade-off between overfitting and correctness, was selected to classify a second set containing 221,884 unclassified tweets. A timeline with the classified tweets was constructed, helping to identify dates with peaks in each polarity and search for events that may have caused the peaks, providing methodological assistance in combating sources of misinformation linked to the spread of anti-vaccination opinion. |
| first_indexed | 2024-03-09T19:25:02Z |
| format | Article |
| id | doaj.art-934f7031ba4b4119a10e617250a644d5 |
| institution | Directory Open Access Journal |
| issn | 2414-6366 |
| language | English |
| last_indexed | 2024-03-09T19:25:02Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tropical Medicine and Infectious Disease |
| spelling | doaj.art-934f7031ba4b4119a10e617250a644d52023-11-24T02:59:51ZengMDPI AGTropical Medicine and Infectious Disease2414-63662022-09-0171025610.3390/tropicalmed7100256Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating MisinformationVictor Diogho Heuer de Carvalho0Thyago Celso Cavalcante Nepomuceno1Thiago Poleto2Jean Gomes Turet3Ana Paula Cabral Seixas Costa4Eixo das Tecnologias, Campus do Sertão, Federal University of Alagoas, Delmiro Gouveia 57480-000, BrazilNúcleo de Tecnologia, Centro Acadêmico do Agreste, Federal University of Pernambuco, Caruaru 55014-900, BrazilDepartamento de Administração, Federal University of Pará, Belém 66075-110, BrazilDepartamento de Engenharia de Produção, Federal University of Pernambuco, Recife 50740-550, BrazilDepartamento de Engenharia de Produção, Federal University of Pernambuco, Recife 50740-550, BrazilThis article presents a study that applied opinion analysis about COVID-19 immunization in Brazil. An initial set of 143,615 tweets was collected containing 49,477 pro- and 44,643 anti-vaccination and 49,495 neutral posts. Supervised classifiers (multinomial naïve Bayes, logistic regression, linear support vector machines, random forests, adaptative boosting, and multilayer perceptron) were tested, and multinomial naïve Bayes, which had the best trade-off between overfitting and correctness, was selected to classify a second set containing 221,884 unclassified tweets. A timeline with the classified tweets was constructed, helping to identify dates with peaks in each polarity and search for events that may have caused the peaks, providing methodological assistance in combating sources of misinformation linked to the spread of anti-vaccination opinion.https://www.mdpi.com/2414-6366/7/10/256COVID-19pandemicsvaccinationBrazilopinion miningtemporal analysis |
| spellingShingle | Victor Diogho Heuer de Carvalho Thyago Celso Cavalcante Nepomuceno Thiago Poleto Jean Gomes Turet Ana Paula Cabral Seixas Costa Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation Tropical Medicine and Infectious Disease COVID-19 pandemics vaccination Brazil opinion mining temporal analysis |
| title | Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation |
| title_full | Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation |
| title_fullStr | Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation |
| title_full_unstemmed | Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation |
| title_short | Mining Public Opinions on COVID-19 Vaccination: A Temporal Analysis to Support Combating Misinformation |
| title_sort | mining public opinions on covid 19 vaccination a temporal analysis to support combating misinformation |
| topic | COVID-19 pandemics vaccination Brazil opinion mining temporal analysis |
| url | https://www.mdpi.com/2414-6366/7/10/256 |
| work_keys_str_mv | AT victordioghoheuerdecarvalho miningpublicopinionsoncovid19vaccinationatemporalanalysistosupportcombatingmisinformation AT thyagocelsocavalcantenepomuceno miningpublicopinionsoncovid19vaccinationatemporalanalysistosupportcombatingmisinformation AT thiagopoleto miningpublicopinionsoncovid19vaccinationatemporalanalysistosupportcombatingmisinformation AT jeangomesturet miningpublicopinionsoncovid19vaccinationatemporalanalysistosupportcombatingmisinformation AT anapaulacabralseixascosta miningpublicopinionsoncovid19vaccinationatemporalanalysistosupportcombatingmisinformation |