What is it about?
Physical distancing (PD) measures were introduced in countries to tackle COVID-19 pandemic. With data extracted from Facebook, we used recurrent neural network to classify public feedback to PD with the health belief model. Data was extracted from the Facebook pages of Ministry of Health of Singapore (MOH), the Centers for Disease Control and Prevention, and Public Health England for the first quarter of 2020. We found that public were discussing more about the susceptibility aspects of PD at the start of 2020 but the narrative changed by end of March where the benefits of PD were more discussed in the three countries
Featured Image
Photo by visuals on Unsplash
Why is it important?
Social media is turning out to be a valuable source for collecting public feedback about government interventions. During the ongoing COVID19 situation, public have started using Facebook and Twitter more to engage with public officials. Through this study, we have shown how a theoretical model such as the health belief can be effectively used to analyze public feedback towards physical distancing. More importantly, by developing a deep learning model, we have automated the classification process to facilitate faster analysis
Perspectives
The challenge in this study was preparing a good training set for the deep learning model. We hope to retrain the models with more examples from other countries
Aravind Sesagiri Raamkumar
National University of Singapore
Read the Original
This page is a summary of: Health Belief Model-based Deep Learning Classifiers for Classifying COVID-19 Social Media Content to Examine Public Behaviors towards Physical Distancing (Preprint), JMIR Public Health and Surveillance, May 2020, JMIR Publications Inc.,
DOI: 10.2196/20493.
You can read the full text:
Contributors
The following have contributed to this page
