Document Classification with Termolator for COVID-19 Literature

The COVID-19 pandemic has led to a multiplicity of research publications related to various aspects of coronavirus. Research topics range from COVID-19 transmission mechanisms to the public health response of various countries, and the publications need to be categorized for easier and more efficient access to resources. This paper explores various machine learning-based document classification techniques to categorize COVID-19 related literature. We integrate a novel terminology dictionary with machine learning models to study the dictionary's impact on the effectiveness of various classification techniques. We report a slight boost to F1 scores as a result of our modifications.