Evaluating the cohesion of municipalities’ discourse during the COVID-19 pandemic

  • Victor Antonio Menuzzo Universidade Estadual de Campinas (UNICAMP)
  • André Santanchè Universidade Estadual de Campinas (UNICAMP)
  • Luiz Gomes-Jr Universidade Tecnológica Federal do Paraná (UTFPR)


Social media has been used as a method to alert and raise awareness among the population to help fight the COVID-19 pandemic. We argue that the discourse of municipalities and their respective mayors may have an influence on the behavior of the population and thus directly impact COVID-19 outcomes. This paper analyzes the diversity and cohesion of these discourses through posts published on Facebook, evaluating (i) diversity of topics discussed, (ii) topic evolution, and (iii) deviation from a central discourse. We also combine this information with epidemiological data to assess impact in the outcomes. In particular, we present two different Latent Dirichlet allocation (LDA) models to analyze how topics are being discussed by municipalities/mayors and compare how cohesion is related to the evolution of the pandemic. Our initial analysis suggests that municipalities tend to employ a unified discourse as a response to the worsening of epidemic outcomes. The results of our study could help to inform governments of better communication strategies in this and future health crisis.
Palavras-chave: COVID-19, discourse analysis, cohesion, LDA, topic modeling


Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. JMLR, 3:993–1022.

de Melo, T. and Figueiredo, C. M. (2020). A first public dataset from brazilian twitter and news on covid-19 in portuguese. Data in brief, 32:106179.

Deerwester, S. et al. (1990). Indexing by latent semantic analysis. JASIST, 41(6):391–407.

Fairclough, N. (2003). Analysing discourse: Textual analysis for social research. Psychology Press.

Fløttum, K. (2010). A linguistic and discursive view on climate change discourse. ASp. la revue du GERAS, (58):19–37.

Gill, R. (2000). Discourse analysis. Qualitative researching with text, image and sound, 1:172–190.

Goyal, N. and Gomeni, R. (2013). A latent variable approach in simultaneous modeling of longitudinal and dropout data in schizophrenia trials. ECNP, 23(11):1570–1576.

Jewett, R. L., Mah, S. M., Howell, N., and Larsen, M. M. (2021). Social cohesion and community resilience during covid-19 and pandemics: A rapid scoping review to inform the united nations research roadmap for covid-19 recovery. IJHS, page 0020731421997092.

Kandula, S., Curtis, D., Hill, B., and Zeng-Treitler, Q. (2011). Use of topic modeling for recommending relevant education material to diabetic patients. volume 2011, page 674. AMIA.

Li, A. et al. (2015). Attitudes towards suicide attempts broadcast on social media: an exploratory study of chinese microblogs. PeerJ, 3:e1209.

Liu, Q. et al. (2020). Health communication through news media during the early stage of the covid-19 outbreak in china: digital topic modeling approach. JMIR, 22(4):e19118.

O’callaghan, D. et al. (2015). An analysis of the coherence of descriptors in topic modeling. Expert Systems with Applications, 42(13):5645–5657.

Rashed, M., Piorkowski, J., and McCulloh, I. (2019). Evaluation of extremist cohesion in a darknet forum using ergm and lda. ASONAM ’19, page 899–902, New York, NY, USA. ACM.

Reed, J. T. (1997). Discourse analysis. A handbook to the exegesis of the New Testament, pages 189–218.

Shahbazi, Z. and Byun, Y.-C. (2020). Analysis of domain-independent unsupervised text segmentation using lda topic modeling over social media contents. Int. J. Adv. Sci. Technol, 29:5993–6014.

Stoica, P., Moses, R. L., et al. (2005). Spectral analysis of signals.

Widdowson, H. G. (2007). Discourse analysis, volume 133. Oxford University Press Oxford.

Zirn, C. and Stuckenschmidt, H. (2014). Multidimensional topic analysis in political texts. DKE, 90:38–53.
MENUZZO, Victor Antonio; SANTANCHÈ, André; GOMES-JR, Luiz. Evaluating the cohesion of municipalities’ discourse during the COVID-19 pandemic. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 36. , 2021, Rio de Janeiro. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 295-300. ISSN 2763-8979. DOI: https://doi.org/10.5753/sbbd.2021.17888.