CoChat

Public Perception of the COVID-19 Pandemic on Twitter: Sentiment Analysis and Topic Modeling Study

Open access
Boon-Itt, Sakun, Skunkan, Yukolpat · 2020 · JMIR Public Health and Surveillance

Published version of a preprint

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Abstract

Background: COVID-19 is a scientifically and medically novel disease that is not fully understood because it has yet to be consistently and deeply studied. Among the gaps in research on the COVID-19 outbreak, there is a lack of sufficient infoveillance data. Objective: The aim of this study was to increase understanding of public awareness of COVID-19 pandemic trends and uncover meaningful themes of concern posted by Twitter users in the English language during the pandemic. Methods: Data mining was conducted on Twitter to collect a total of 107,990 tweets related to COVID-19 between December 13 and March 9, 2020. The analyses included frequency of keywords, sentiment analysis, and topic modeling to identify and explore discussion topics over time. A natural language processing approach and the latent Dirichlet allocation algorithm were used to identify the most common tweet topics as well as to categorize clusters and identify themes based on the keyword analysis. Results: The results indicate three main aspects of public awareness and concern regarding the COVID-19 pandemic. First, the trend of the spread and symptoms of COVID-19 can be divided into three stages. Second, the results of the sentiment analysis showed that people have a negative outlook toward COVID-19. Third, based on topic modeling, the themes relating to COVID-19 and the outbreak were divided into three categories: the COVID-19 pandemic emergency, how to control COVID-19, and reports on COVID-19. Conclusions: Sentiment analysis and topic modeling can produce useful information about the trends in the discussion of the COVID-19 pandemic on social media as well as alternative perspectives to investigate the COVID-19 crisis, which has created considerable public awareness. This study shows that Twitter is a good communication channel for understanding both public concern and public awareness about COVID-19. These findings can help health departments communicate information to alleviate specific public concerns about the disease.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/21978

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Frequency of retweets regarding the COVID-19 pandemic from December 13, 2009, to March 9, 2020. (A) A novel coronavirus was isolated; (B) the first fatal case was reported; (C) the first case of COVID-19 in the United States was confirmed; (D) 835 cases were reported in China; (E) the World Health Organization (WHO) declared a public health emergency of international concern; (F) the WHO announced the name “COVID-19”; (G) infections spiked in Italy and the rest of Europe; (H) the number of COVID-19 cases surpassed 100,000.
Figure 1 Frequency of retweets regarding the COVID-19 pandemic from December 13, 2009, to March 9, 2020. (A) A novel coronavirus was isolated; (B) the first fatal case was reported; (C) the first case of COVID-19 in the United States was confirmed; (D) 835 cases were reported in China; (E) the World Health Organization (WHO) declared a public health emergency of international concern; (F) the WHO announced the name “COVID-19”; (G) infections spiked in Italy and the rest of Europe; (H) the number of COVID-19 cases surpassed 100,000.CC BY · PubMed Central
Figure 2 Frequencies of the keywords outbreak and pandemic on Twitter.
Figure 2 Frequencies of the keywords outbreak and pandemic on Twitter.CC BY · PubMed Central
Figure 3 Trend lines indicating the word frequencies of four key COVID-19 symptoms on Twitter.
Figure 3 Trend lines indicating the word frequencies of four key COVID-19 symptoms on Twitter.CC BY · PubMed Central
Figure 4 Word cloud showing the keywords appearing most frequently in tweets related to COVID-19.
Figure 4 Word cloud showing the keywords appearing most frequently in tweets related to COVID-19.CC BY · PubMed Central
Figure 6 Sentiment analysis of negative (red line) and positive (blue line) tweets related to COVID-19.
Figure 6 Sentiment analysis of negative (red line) and positive (blue line) tweets related to COVID-19.CC BY · PubMed Central
Figure 7 Sentiment analysis based on terms in the National Research Council sentiment lexicon.
Figure 7 Sentiment analysis based on terms in the National Research Council sentiment lexicon.CC BY · PubMed Central
Figure 8 Sentiment wheel showing the emotional quotients of the studied tweets.
Figure 8 Sentiment wheel showing the emotional quotients of the studied tweets.CC BY · PubMed Central
Figure 10 Word cloud showing the most frequently mentioned words and their related emotions (categorized by color).
Figure 10 Word cloud showing the most frequently mentioned words and their related emotions (categorized by color).CC BY · PubMed Central
Figure 11 Word cloud showing the frequency of words associated with six identified topics: (1) reports on deadly pneumonia new cases and deaths of coronavirus outbreak from China; (2) the epidemic situation and confirmed cases of COVID-19; (3) knowledge about COVID-19 obtained from news reports; (4) the spread of COVID-19 from overseas to the US and how to control the disease; (5) health concerns and fear as COVID-19 is declared an emergency worldwide; (6) news and information reports on social media about the epidemic.
Figure 11 Word cloud showing the frequency of words associated with six identified topics: (1) reports on deadly pneumonia new cases and deaths of coronavirus outbreak from China; (2) the epidemic situation and confirmed cases of COVID-19; (3) knowledge about COVID-19 obtained from news reports; (4) the spread of COVID-19 from overseas to the US and how to control the disease; (5) health concerns and fear as COVID-19 is declared an emergency worldwide; (6) news and information reports on social media about the epidemic.CC BY · PubMed Central
Figure 12 The per-topic-per-word probabilities produced by latent Dirichlet allocation by extracting the beta matrix.
Figure 12 The per-topic-per-word probabilities produced by latent Dirichlet allocation by extracting the beta matrix.CC BY · PubMed Central
Figure 13 Word cloud and topic modeling of keywords related to the COVID-19 outbreak, organized into three topics: (1) The new strain of pneumonia identified in Wuhan, China; (2) the mysterious illness caused by the novel virus; (3) the warning from China that the death toll of COVID-19 could increase.
Figure 13 Word cloud and topic modeling of keywords related to the COVID-19 outbreak, organized into three topics: (1) The new strain of pneumonia identified in Wuhan, China; (2) the mysterious illness caused by the novel virus; (3) the warning from China that the death toll of COVID-19 could increase.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 4

  1. Jahanbin, K, 2020, Asian Pac J of Trop Med 2020; 13, 13, 378
  2. Murray, C, ArXiv
  3. 10.2196/19087 · DOI
  4. Kleinberg, B, ArXiv

Cited by

See all 486

Metadata

Authors
Boon-Itt, S., & Skunkan, Y.
Affiliations
Bangkok Christian Hospital (TH)
Venue
JMIR Public Health and Surveillance
Published
2020-11-11
Volume
6
Issue
4
Pages
e21978
ISSN
2369-2960 (ISSN-L)
OpenAlex
W3094221957
Cited by
486
References
43
Citations by year
2026: 23 · 2025: 67 · 2024: 77 · 2023: 118 · 2022: 115 · 2021: 84 · 2020: 2
FWCI
31.35
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR Public Health and Surveillance (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Social Sciences › Communication › Communication and COVID-19 Impact
  • Health Sciences › Medicine › Epidemiology › Data-Driven Disease Surveillance
Keywords
COVID-19 pandemic, public perception, Twitter, social media discourse, public awareness, sentiment analysis, topic modeling, pandemic control measures, health communication, infoveillance
MeSH terms
COVID-19, Humans, Health Knowledge, Attitudes, Practice, Models, Psychological, Natural Language Processing, Data Mining, Pandemics, Social Media

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.