Leveraging Natural Language Processing to Mine Issues on Twitter During the COVID-19 Pandemic

The recent global outbreak of the coronavirus disease (COVID-19) has spread\nto all corners of the globe. The international travel ban, panic buying, and\nthe need for self-quarantine are among the many other social challenges brought\nabout in this new era. Twitter platforms have been used in various public\nhealth studies to identify public opinion about an event at the local and\nglobal scale. To understand the public concerns and responses to the pandemic,\na system that can leverage machine learning techniques to filter out irrelevant\ntweets and identify the important topics of discussion on social media\nplatforms like Twitter is needed. In this study, we constructed a system to\nidentify the relevant tweets related to the COVID-19 pandemic throughout\nJanuary 1st, 2020 to April 30th, 2020, and explored topic modeling to identify\nthe most discussed topics and themes during this period in our data set.\nAdditionally, we analyzed the temporal changes in the topics with respect to\nthe events that occurred during this pandemic. We found out that eight topics\nwere sufficient to identify the themes in our corpus. These topics depicted a\ntemporal trend. The dominant topics vary over time and align with the events\nrelated to the COVID-19 pandemic.\n