Analyzing society anti-vaccination attitudes towards COVID-19: combining latent dirichlet allocation and fuzzy association rule mining with a fuzzy cognitive map

Abstract

COVID-19 has been declared a pandemic and countries are tackling this disease either through preventative measures such as lockdown and sanitization or through curative ones such as medication, isolation, and so on. Some people believe that vaccination is the best way to prevent this disease, while others disagree. Society’s attitudes toward vaccination can be influenced by a variety of factors such as misunderstanding, ambiguity, lack of knowledge. The proposed study’s goal is to better understand people’s attitudes regarding vaccination by focusing on key topics related to COVID-19 anti-vaccine tweets. Tweets are obtained over a period based on the number of COVID-19 cases by utilizing the “anti-vaccine” keyword rather than the “vaccine” keyword. Furthermore, in addition to people perceptions and attitudes toward anti-vaccination, the causal relationship between each topic is investigated. As a result, latent dirichlet allocation (LDA), fuzzy association rule mining (FARM), fuzzy cognitive map (FCM), and fuzzy c-means are used to conduct a complete study. Topics are analyzed independently using clustering and scenario analysis. The findings demonstrate the most common topics in anti-vaccination tweets, as well as the influence of each topic on the others.

Public Opinion Mining on Construction Health and Safety: Latent Dirichlet Allocation Approach

“…where C is the corpus of the documents (D), x is each document topic distribution's Dirichlet previous concentration parameter, while b refers to the corpus-level parameter, Φ d represents the document-level variable, n is the number of words in the document, T a is the topic assignment, W dn refers to the nth word in the dth document, and m represents the documents that needed to be analyzed [42]. The LDA topic model was analyzed from the KH Coder via the Fit a Topic Model.…”