A New Study by Angelopoulou and Colleagues Aims to Educate Policymakers on Achieving Public Support

In their study forthcoming in IEEE Transactions on Computational Social Systems, TSYS School’s Anastasia Angelopoulou and her research colleagues at Auburn University assert that public sentiment can impact the implementation of public policies and even cause policy failure if public support does not exist.  This means that knowledge of public sentiment concerning new and emerging policies is critical for policymakers.  The COVID-19 pandemic offers a useful example, given that various precautionary measures have been either implemented or suggested in an attempt to delay or mitigate the spread of the virus.  Angelopoulou’s new study presents a framework that applies natural language processing (NLP) techniques in order to characterize the public sentiment on three prominent COVID-19 mitigation measures – mask wearing, social distancing, and quarantining – as shared by Twitter users in the United States. 

As part of the framework, the researchers apply a bigram graph-based approach to visualize the most frequent topics in Twitter discussions during the COVID-19 pandemic in an effort to provide insights into the most commonly discussed topics among Twitter users with similar demographic characteristics (e.g., age and gender).  Bigram analyses indicates that Twitter discussions containing positive sentiment prevailed and revolved around the benefits of the measures and trust in the government, while the topics of negative sentiment involved conspiracy theories, skepticism, and distrust of government mandates.  The analyses also suggest that discussions among people in the 19 to 29 age bracket, and those over 40 years old, focus on government officials and political parties, benefits or inefficiency of mitigation measures, and conspiracy theories more often than other demographic groups.