Download PDFOpen PDF in browserDetermining Anti-Curve-Flattening Behaviors for COVID-19 in the United States10 pages•Published: June 9, 2021AbstractCOVID-19 has arguably impacted every dimension of social living — be that employ- ment, schooling, healthcare or recreational activities. In a matter of months, businesses have shut down and the workforce and schools have been redirected to online work in many regions of the world. One key element of the North American pandemic response has been the emphasis that the spread or prevention of the pandemic is largely dependent on the measures taken by residents of any region. As such, our research focuses on outlining the factors that determine if an individual is less likely to take this pandemic seriously (i.e. is taking fewer measures to prevent the spread of COVID-19). We have analyzed the results of a U.S. wide COVID-impact survey using random forest classification (RFC) to associate individual demographic factors to measures taken against the pandemic such as washing/sanitizing hands. Our results indicate that the top three influential factors are household size, the number of adults living in one household and the health of the respon- dent (poor to excellent). Using these insights, we used association rules to determine key combinations of features that may lead to an apathetic response to a global pandemic in U.S. citizens, such as lower income households.Keyphrases: association rules, covid 19, data mining, machine learning, prevention, random forest In: Yan Shi, Gongzhu Hu, Takaaki Goto and Quan Yuan (editors). CAINE 2020. The 33rd International Conference on Computer Applications in Industry and Engineering, vol 75, pages 22-31.
|
