Perception of the Brazilian population related to COVID-19 vaccines on X (former Twitter): sentiment analysis
DOI:
https://doi.org/10.30968/jhphs.2026.171.1375Abstract
Objectives: To analyze the perception of X/Twitter users regarding the COVID-19 vaccines made available by the Brazilian Ministry of Health. Methods: tweets published during the year 2021 made available by the Application Programming Interface of the Twitter platform were analyzed. The Python programming language was used for extracting and processing data, and the Power BI software was used for the generation of graphics. A lexicon in the Brazilian Portuguese language has been developed. The Extra Trees model was selected because it demonstrated the best performance among the models evaluated, showing a greater ability to correctly identify positive, negative, and neutral sentiments. Results: 2,202,571 tweets were extracted referring for the following vaccines: CoronaVac (642,465); AstraZeneca (472,449); Janssen (162,056) and Pfizer (952,601). In January 2021, more than 100,000 tweets related to CoronaVac were identified. Of these, 41.7% were related to positive sentiments and only 18.5% to negative sentiments. Considering the entire year of 2021, the Janssen vaccine among the more than 50,000 publications analyzed, 40.4% were neutral and 33.9% negative. In June 2021, a total of 101,952 vaccine-related posts were identified on the AstraZeneca vaccine, 63.66% with neutral sentiments. Regarding the posts of the Pfizer vaccine, on May 1, 2021, a total of 124,058 posts were found, being found approximately 54.52% of the posts associated with neutral feeling. Conclusion: most of the sentiments obtained for all vaccines were neutral, however it was also possible to observe that the CoronaVac, despite the negative publicity, was widely accepted by the population having most of the sentiments expressed in a positive way if considered with the data of the other vaccines.
Downloads
References
1. Medeiros EAS. Desafios para o enfrentamento da pandemia COVID-19 em hospitais universitários. Ver Paul Pediatr. 2020;38:e2020086. doi: 10.1590/1984-0462/2020/38/2020086
2. Almars AM, Atlam ES, Noor TH, et al. Users opinion and emotion understanding in social media regarding COVID-19 vaccine. Computing. 2022;104(6):1481-1496. doi:10.1007/s00607-022-01062-9
3. Fernandes-de-Oliveira G, Massarani L, Oliveira T, et al. A vacina no Instagram: estudo das emoções expressas no contexto brasileiro. Rev Mediterr Comun. 2023;14(2):283-298. doi:10.14198/medcom.24190
4. Jang H, Rempel E, Roth D, et al. Tracking COVID-19 discourse on Twitter in North America: Infodemiology study using topic modeling and aspect-based sentiment analysis. J Med Internet Res. 2021;23(2):e25431. doi:10.2196/25431
5. Monari ACP, Araújo KM de, Souza MR de, et el. Legitimando um populismo anticiência: análise dos argumentos de Bolsonaro sobre a vacinação contra Covid-19 no Twitter. Liinc Em Rev. 2021;17(1):e5707. doi:10.18617/liinc.v17i1.5707
6. Massarani L, Brotas A, Costa MCR, et al. Vacinas contra a COVID-19 e o combate à desinformação na cobertura da Folha de S. Paulo. Front - estud midiáticos. 2021;23(2):29-43. doi:10.4013/fem.2021.232.03
7. Bisol J. Politização da vacina é irresponsabilidade sanitária. Cad Ibero-Am Direito Sanit. 2020;9(4):192-197. doi:10.17566/ciads.v9i4.751
8. Sharma C, Whittle S, Haghighi PD, et al. Sentiment analysis of social media posts on pharmacotherapy: A scoping review. Pharmacol Res Perspect. 2020;8(5). doi:10.1002/prp2.640
9. Moreira VDS, Siqueira SW, Andrade L, Pimentel M. Análise de Sentimentos: Comparando o uso de ferramentas e a análise humana. Florianópolis: Anais do Simpósio Brasileiro de Sistemas de Informação; 2016.
10. Bee GR, Pinto DD, Da Silva ACCA, et al. Vacinas contra COVID-19 disponíveis no Brasil / Vaccines against COVID-19 available in Brazil. Braz J Dev. 2022;8(1):6246-6263. doi:10.34117/bjdv8n1-422
11. Mitchell JBO. Three machine learning models for the 2019 Solubility Challenge. ADMET DMPK. 2020;8(3):215-250. doi:10.5599/admet.835
12. Ferreira J, Oliveira HG, Rodrigues R. Improving NLTK for Processing Portuguese. Open Access Series in Informatics. 2019;74:18:1–18:9. doi:10.4230/OASIcs.SLATE.2019.18
13. Saleiro P, Sarmento L, Rodrigues EM, et al. Learning Word Embeddings from the Portuguese Twitter Stream: A Study of Some Practical Aspects. arXiv preprint. 2017;v(1):1-12. doi:10.48550/arXiv.1709.00947
14. Garcia K, Berton L. Topic detection and sentiment analysis in Twitter content related to COVID-19 from Brazil and the USA. Appl Soft Comput. 2021;101(107057):107057. doi:10.1016/j.asoc.2020.107057
15. de Melo T, Figueiredo CMS. Comparing news articles and tweets about COVID-19 in Brazil: Sentiment analysis and topic modeling approach. JMIR Public Health Surveill. 2021;7(2):e24585. doi:10.2196/24585
16. Liu S, Liu J. Public attitudes toward COVID-19 vaccines on English-language Twitter: A sentiment analysis. Vaccine. 2021;39(39):5499-5505. doi:10.1016/j.vaccine.2021.08.058
17. Barreto S, Moura R, Carvalho J, et al. Sentiment analysis in tweets: an assessment study from classical to modern word representation models. Data Min Knowl Discov. 2023;37(1):318-380. doi:10.1007/s10618-022-00853-0
18. Sun X, Wagner AL, Ji J, et al. A conjoint analysis of stated vaccine preferences in Shanghai, China. Vaccine. 2020;38(6):1520-1525. doi:10.1016/j.vaccine.2019.11.062
19. Wagner AL, Boulton ML, Sun X, et al. Perceptions of measles, pneumonia, and meningitis vaccines among caregivers in Shanghai, China, and the health belief model: a cross-sectional study. BMC Pediatr. 2017;17(1). doi:10.1186/s12887-017-0900-2
20. Roy DN, Biswas M, Islam E, et al. Potential factors influencing COVID-19 vaccine acceptance and hesitancy: A systematic review. PLoS One. 2022;17(3):e0265496. doi:10.1371/journal.pone.0265496
21. Carvalho EM de, Santos Junior MA do, Neves LFF, et al. Vacinas e redes sociais: o debate em torno das vacinas no Instagram e Facebook durante a pandemia de COVID-19 (2020-2021). Cad Saude Publica. 2022;38(11):e00054722. doi:10.1590/0102-311xpt054722
22. Fleury S, Fava VMD. Vacina contra Covid-19: arena da disputa federativa brasileira. Saúde em Debate. 2022;46(spe1):248-264. doi:10.1590/0103-11042022e117
23. Galhardi CP, Freire NP, Fagundes MCM, et al. Fake News and vaccine hesitancy in the COVID-19 pandemic in Brazil. Cien Saude Colet. 2022;27(5):1849-1858. doi:10.1590/1413-81232022275.24092021en
24. Jaworsky BN, Qiaoan R. The politics of blaming: The narrative battle between China and the US over COVID-19. J Chin Polit Sci. 2021;26(2):295-315. doi:10.1007/s11366-020-09690-8
25. Huangfu L, Mo Y, Zhang P, et al. COVID-19 vaccine tweets after vaccine rollout: Sentiment–based topic modeling. J Med Internet Res. 2022;24(2):e31726. doi:10.2196/31726
26. de Figueiredo A, Larson HJ. Exploratory study of the global intent to accept COVID-19 vaccinations. Commun Med (Lond). 2021;1(1):1-10. doi:10.1038/s43856-021-00027-x
27. Fleury S, Fava VMD. Vacina contra Covid-19: arena da disputa federativa brasileira. Saúde em Debate. 2022;46(spe1):248-264. doi:10.1590/0103-11042022e117
28. Milani Rodrigues S, Pestillo de Oliveira L, França Garcia L. Imunização no Brasil: reflexões histórico-social e bioética da vacinação na promoção da saúde. Rev Latinoam Bioet. 2025;25(1):57-72. doi:10.18359/rlbi.6839
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors hereby transfer, assign, or otherwise convey to JHPHS : (1) the right to grant permission to republish or reprint the stated material, in whole or in part, without a fee; (2) the right to print republish copies for free distribution or sale; and (3) the right to republish the stated material in any format (electronic or printed). In addition, the undersigned affirms that the article described above has not previously been published, in whole or part, is not subject to copyright or other rights except by the author(s), and has not been submitted for publication elsewhere, except as communicated in writing to JHPHS with this document.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-BY) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Serlf-archiving policy
This journal permits and encourages authors to post and archive the final pdf of the articles submitted to the journal on personal websites or institutional repositories after publication, while providing bibliographic details that credit its publication in this journal.
