Analysis of publications on COVID-19 vaccines by Brazilians and the President of Brazil on Twitter

• Adriano Madureira Federal University of Pará
• Douglas A. Vidal Federal University of Pará
• Harold de M. Junior State University of Rio de Janeiro
• Karla Figueiredo State University of Rio de Janeiro
• Lucas D. Moreira Medonça Federal University of Pará
• Marcos César da Rocha Seruffo Federal University of Pará
• Rita Paulino Federal University of Santa Catarina
• Yomara P. Pires Federal University of Pará

DOI: https://doi.org/10.5753/ersirj.2021.16983

Abstract

Since the beginning of 2020, the world has been experiencing a health crisis caused by COVID-19. Although the pandemic is devastating around the world, the actions to fight it and the impacts it suffers are different among nations. However, the vaccine is one of the main tools for controlling the pandemic. In this scenario, Online Social Networks (OSN) have become a significant space for civic and political activity, being among the most used information sources in the world. This article aims to report an analysis of publications on vaccines against COVID-19 by Brazilian users and the president of Brazil on the Twitter platform. Machine Learning Techniques were used and the results show that the Support Vector Machine model was the one that achieved the best performance with 60.72% accuracy with ReliefF parameter extraction for the analysis of tweets that indicated which vaccines were the most mentioned in the president's and users' profiles.

Keywords: Machine Learning, Online Social Media, Support VectorMachine, LIWC

References

Bokang et al. An Ensemble Machine Learning Approach to Understanding the Effect of a Global Pandemic on Twitter Users’ Attitudes, mar. 2021. https://doi.org/10.15837/ijccc.2021.2.4207.

Breiman, L. (2001). Random forests. Machine learning, v. 45(1), p. 5-32.

Dodds P.S, J. R. Minot, M. V. Arnold, T. Alshaabi, J. L. Adams, D. R. Dewhurst, A. J. Reagan, and C. M. Danforth. Fame and Ultrafame: Measuring and comparing daily levels of ‘being talked about’ for United States’ presidents, their rivals, God, countries, and Kpop, Sept. 2019.

Gonzalez-Padilla, Daniel A. and Tortolero-Blanco, Leonardo. Social media influence in the COVID-19 Pandemic. Epub July 27, 2020. https://doi.org/10.1590/s1677-5538.ibju.2020.s121

Harris, E. (2002). Information Gain Versus Gain Ratio: A Study of Split Method Biases.

Jurasfsky, D.; Martin, J. H. Speech and Language Processing: An Introduction to Natural Language Processing, Comp. Linguistics, and Speech Recognition. 2000.

Kaur, Chhinder; Sharma, Anand. Twitter Sentiment Analysis on Coronavirus using Textblob. EasyChair, 2020.

Kecman, Vojislav. (2005). Support Vector Machines – An Introduction 10.1007/10984697_1.

Liu, H., & Motoda, H. (Eds.). (2007). Computational methods of feature selection.

Malavé, Mayra. O papel das redes sociais durante a pandemia. URL: http://www.iff.fiocruz.br/index.php/8-noticias/675-papel-redes-sociais.

Malinen S. Koivula A. and Koiranen I. (2020) How do Digital Divides Determine Social Media Users’ Aspirations to Influence Others?. July 22–24, 2020, https://doi.org/10.1145/3400806.3400823

Tausczik YR, Pennebaker JW. The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods. Journal of Language and Social Psychology. 2010;29(1):24-54. doi:10.1177/0261927X09351676

Xavier, Fernando et al. Análise de redes sociais como estratégia de apoio à vigilância em saúde durante a COVID-19.Epub July 10, 2020. http://dx.doi.org/10.1590/s0103-4014.2020.3499.016.