Extracting Major Topics of COVID-19 Related Tweets

TL;DR

This paper applies topic modeling to COVID-19 related tweets during quarantine to identify major topics and analyze their temporal and spatial trends worldwide and in four specific countries.

Contribution

It introduces a method using LDA to extract and name COVID-19 topics from tweets and analyzes their temporal dynamics across different regions.

Findings

Identified key COVID-19 topics such as 'masking' and 'social distance'

Revealed changing user focus on topics over time

Provided insights into regional differences in topic trends

Abstract

With the outbreak of the Covid-19 virus, the activity of users on Twitter has significantly increased. Some studies have investigated the hot topics of tweets in this period; however, little attention has been paid to presenting and analyzing the spatial and temporal trends of Covid-19 topics. In this study, we use the topic modeling method to extract global topics during the nationwide quarantine periods (March 23 to June 23, 2020) on Covid-19 tweets. We implement the Latent Dirichlet Allocation (LDA) algorithm to extract the topics and then name them with the "reopening", "death cases", "telecommuting", "protests", "anger expression", "masking", "medication", "social distance", "second wave", and "peak of the disease" titles. We additionally analyze temporal trends of the topics for the whole world and four countries. By analyzing the graphs, fascinating results are obtained from altering users' focus on topics over time.