ABSTRACT
Vaccines are an old technique, known and used for over 200 years. However, it is likely that the arrival of the COVID-19 pandemic made the public debate around this technology become polarized at a level never seen before. Thus, this work aims to determine and understand factors that lead Brazilian users on Twitter to be favorable or not to vaccines by first determining users' stances in relation to the vaccination topic and then using Machine Learning methods to infer demographic information and determine which are the socio-demographic factors that cause the greatest impact on users' opinions on vaccines. First, a data set composed of relevant demographic information from users who stand for or against vaccines was generated. Then, from the collected data, charts were generated showing the distributions of the obtained demographic information and Machine Learning algorithms were applied to the data set in order to generate relevant models for the research. Finally, the information collected in the previous steps was analyzed in order to draw relevant conclusions about how each demographic factor considered influences the formation of Twitter users opinions on vaccines and their use. The methodology proposed produced informative and pertinent results, and it was possible to determine that age and location are the factors that cause the most significant influence on users' opinions. Our work proposes an efficient and agile framework that can be easily and readily implemented and extended to understand not only stances on vaccines, but also opinions on any subject of public debate. © 2021 IEEE.