Background COVID-19, caused by SARS-CoV-2, has led to a global pandemic. The World Health Organization has also declared an infodemic (ie, 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. Objective This research analyzes the public discourse on COVID-19. It characterizes risk communication patterns in four Asian countries with outbreaks at varying degrees of severity: South Korea, Iran, Vietnam, and India. Methods We collected tweets on COVID-19 from four Asian countries in the early phase of the disease outbreak from January to March 2020. The data set 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. The extracted topics were evaluated qualitatively based on their semantic meanings. Results This research found that each government’s official phases of the epidemic were not well aligned with the degree of public attention represented by the daily tweet counts. Inspired by the issue-attention cycle theory, the presented natural language processing 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. Conclusions This paper compares similarities and differences of pandemic-related social media discourse in Asian countries. We observed multiple prominent peaks in the daily tweet counts across all countries, indicating multiple issue-attention cycles. Our analysis identified which topics the public concentrated on; some of these topics were related to misinformation and hate speech. These findings and the ability to quickly identify key topics can empower global efforts to fight against an infodemic during a pandemic.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

BACKGROUND The novel coronavirus disease (hereafter COVID-19) caused by severe acute respiratory coronavirus 2 (SARS-CoV-2) has caused a global pandemic. During this time, a plethora of information regarding COVID-19 containing both false information (misinformation) and accurate information circulated on social media. The World Health Organization has declared a need to fight not only the pandemic but also the infodemic (a portmanteau of information and pandemic). In this context, it is critical to analyze the quality and veracity of information shared on social media and the evolution of discussions on major topics regarding COVID-19. OBJECTIVE This research characterizes risk communication patterns by analyzing public discourse on the novel coronavirus in four Asian countries that suffered outbreaks of varying degrees of severity: South Korea, Iran, Vietnam, and India. METHODS We collect tweets on COVID-19 posted from the four Asian countries from the start of their respective COVID-19 outbreaks in January until March 2020. We consult with locals and utilize relevant keywords from the local languages, following each country's tweet conventions. We then utilize a natural language processing (NLP) method to learn topics in an unsupervised fashion automatically. Finally, we qualitatively label the extracted topics to comprehend their semantic meanings. RESULTS We find that the official phases of the epidemic, as announced by the governments of the studied countries, do not align well with the online attention paid to COVID-19. Motivated by this misalignment, we develop a new natural language processing method to identify the transitions in topic phases and compare the identified topics across the four Asian countries. We examine the time lag between social media attention and confirmed patient counts. We confirm an inverse relationship between the tweet count and topic diversity. CONCLUSIONS Through the current research, we observe similarities and differences in the social media discourse on the pandemic in different Asian countries. We observe that once the daily tweet count hits its peak, the successive tweet count trend tends to decrease for all countries. This phenomenon aligns with the dynamics of the issue-attention cycle, an existing construct from communication theory conceptualizing how an issue rises and falls from public attention. Little work has been performed to identify topics in online risk communication by collectively considering temporal tweet trends in different countries. In this regard, if a critical piece of misinformation can be detected at an early stage in one country, it can be reported to prevent the spread of misinformation in other countries. Therefore, this work can help social media services, social media communicators, journalists, policymakers, and medical professionals fight the infodemic on a global scale. CLINICALTRIAL N/A

BACKGROUND COVID-19, caused by SARS-CoV-2, has led to a global pandemic. The World Health Organization has also declared an infodemic (ie, 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. OBJECTIVE This research analyzes the public discourse on COVID-19. It characterizes risk communication patterns in four Asian countries with outbreaks at varying degrees of severity: South Korea, Iran, Vietnam, and India. METHODS We collected tweets on COVID-19 from four Asian countries in the early phase of the disease outbreak from January to March 2020. The data set 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. The extracted topics were evaluated qualitatively based on their semantic meanings. RESULTS This research found that each government’s official phases of the epidemic were not well aligned with the degree of public attention represented by the daily tweet counts. Inspired by the issue-attention cycle theory, the presented natural language processing 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. CONCLUSIONS This paper compares similarities and differences of pandemic-related social media discourse in Asian countries. We observed multiple prominent peaks in the daily tweet counts across all countries, indicating multiple issue-attention cycles. Our analysis identified which topics the public concentrated on; some of these topics were related to misinformation and hate speech. These findings and the ability to quickly identify key topics can empower global efforts to fight against an infodemic during a pandemic.

No abstract