COVID-19 Discourse on Twitter: Case Study of Risk Communication in Four Asian Countries.

Abstract

BACKGROUND\nThe novel coronavirus disease (COVID-19) caused by severe acute respiratory coronavirus 2 (SARS-CoV-2) has led to a global pandemic. The World Health Organization declared infodemic, i.e., a plethora of information regarding COVID-19 containing both false and accurate information circulated on the Internet. Hence it has become critical to test the veracity of information shared online and analyze the evolution of discussed topics among citizens related to the pandemic.\n\n\nOBJECTIVE\nThis research analyzes the public discourse on the novel coronavirus. It characterizes risk communication patterns in four Asian countries that suffered outbreaks at varying degrees of severity: South Korea, Iran, Vietnam, and India.\n\n\nMETHODS\nWe collected tweets on COVID-19 from four Asian countries in the early phase of the disease outbreak from January to March 2020. The dataset was collected by relevant keywords in each language, as suggested by locals. We present a method to automatically extract a time-topic cohesive relationship in an unsupervised fashion based on natural language processing (NLP). The extracted topics were evaluated qualitatively based on their semantic meanings.\n\n\nRESULTS\nThis research finds that each government s official phases of the epidemic in the studied countries do not align well with the degree of public attention represented by the daily tweet counts. Inspired by the issue-attention cycle theory, the presented NLP model can identify meaningful transition phases in the discussed topics among citizens. The analysis revealed an inverse relationship between the tweet count and topic diversity.\n\n\nCONCLUSIONS\nThis paper compares similarities and differences in the pandemic-related social media discourse in Asian countries. We observe multiple prominent peaks in the daily tweet count across all countries, indicating multiple issue-attention cycles. Our analysis identifies which topics the public concentrated on; some of these topics turned out to be related to misinformation and hate speech. These findings and the ability to quickly identify key topics empower global efforts to fight against the infodemic during a pandemic.\n\n\nCLINICALTRIAL