Disparity-aware Pandemic Response Classification by Fine-Tuning Transfer Learning Approach

Interpersonal communications are being continuously passed over social media networks, and millions of users are interacting and sharing information with each other. In the COVID-19 pandemic crisis, social media platforms ignited with heated discussions between believers, deniers, and hesitating people because of the uncertainty and sometimes dis- and mis-information about the pandemic. Healthcare professional and public health authorities are also utilizing social media platforms to update the public about COVID-19 and vaccinations' impact on the personal health. However, they struggle to control the vast amount of hoaxes and rumors about the pandemic. While regardless the information source, people share and interact in different ways. Some users postulate that the information is a granted truth while some others do a fact-check. In either cases, people will have partial or full influence on others' believe. In this research, we scrutinize the effects of transfer learning across different social media platforms. We utilize different classifiers on the datasets separately and collectively to learn more about users' sentiments and reactions to healthcare statements made by authorities at specific times. Our findings show that transfer learning has little impact on how well classifiers function.