ABSTRACT
During the COVID-19 pandemic many people used social media to seek information about the disease. In addition, these platforms were used to share news and opinions on issues related to COVID-19, such as vaccines and isolation policies. Extracting useful information for public health from these platforms efficiently poses some challenges due to the characteristics of social networks. Therefore, this article presents a method combining clustering and natural language processing for extracting information about users and their posts on social networks about COVID-19. The results show that the combination of clustering methods and textual analysis can reveal valuable information for public health using data from social networks. Future studies can employ this proposed method in order to get real-time information during future epidemics © 2022 IEEE.
ABSTRACT
The COVID-19 pandemic has affected the entire world, causing millions of deaths. In addition to this disease, many countries also periodically face outbreaks of other diseases, such as dengue. Although the two diseases have their specific characteristics, there may be common factors affecting them. Knowing these factors is essential for governments to plan actions to mitigate the impacts of future epidemics. This research aims to analyze data from several dimensions to identify the critical success factors for the fight against dengue and COVID-19. For this, Data Science techniques were applied to data from 645 cities in the State of São Paulo, Brazil. The results provide important information that may explain why some locations have been more successful than others in fighting those diseases, as well as identifying the common factors that may also impact other diseases. © 2022 IEEE.