{"title":"Do we listen to what we are told? An empirical study on human behaviour during the COVID-19 pandemic: neural networks vs. regression analysis","authors":"Yuxi Heluo, Kexin Wang, Charles W. Robson","doi":"arxiv-2311.13046","DOIUrl":null,"url":null,"abstract":"In this work, we contribute the first visual open-source empirical study on\nhuman behaviour during the COVID-19 pandemic, in order to investigate how\ncompliant a general population is to mask-wearing-related public-health policy.\nObject-detection-based convolutional neural networks, regression analysis and\nmultilayer perceptrons are combined to analyse visual data of the Viennese\npublic during 2020. We find that mask-wearing-related government regulations\nand public-transport announcements encouraged correct mask-wearing-behaviours\nduring the COVID-19 pandemic. Importantly, changes in announcement and\nregulation contents led to heterogeneous effects on people's behaviour.\nComparing the predictive power of regression analysis and neural networks, we\ndemonstrate that the latter produces more accurate predictions of population\nreactions during the COVID-19 pandemic. Our use of regression modelling also\nallows us to unearth possible causal pathways underlying societal behaviour.\nSince our findings highlight the importance of appropriate communication\ncontents, our results will facilitate more effective non-pharmaceutical\ninterventions to be developed in future. Adding to the literature, we\ndemonstrate that regression modelling and neural networks are not mutually\nexclusive but instead complement each other.","PeriodicalId":501487,"journal":{"name":"arXiv - QuantFin - Economics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2311.13046","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this work, we contribute the first visual open-source empirical study on
human behaviour during the COVID-19 pandemic, in order to investigate how
compliant a general population is to mask-wearing-related public-health policy.
Object-detection-based convolutional neural networks, regression analysis and
multilayer perceptrons are combined to analyse visual data of the Viennese
public during 2020. We find that mask-wearing-related government regulations
and public-transport announcements encouraged correct mask-wearing-behaviours
during the COVID-19 pandemic. Importantly, changes in announcement and
regulation contents led to heterogeneous effects on people's behaviour.
Comparing the predictive power of regression analysis and neural networks, we
demonstrate that the latter produces more accurate predictions of population
reactions during the COVID-19 pandemic. Our use of regression modelling also
allows us to unearth possible causal pathways underlying societal behaviour.
Since our findings highlight the importance of appropriate communication
contents, our results will facilitate more effective non-pharmaceutical
interventions to be developed in future. Adding to the literature, we
demonstrate that regression modelling and neural networks are not mutually
exclusive but instead complement each other.