Topics, Trends, and Sentiments of Tweets About the COVID-19 Pandemic: Temporal Infoveillance Study
Open accessPublished version of a preprint
The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Background: With restrictions on movement and stay-at-home orders in place due to the COVID-19 pandemic, social media platforms such as Twitter have become an outlet for users to express their concerns, opinions, and feelings about the pandemic. Individuals, health agencies, and governments are using Twitter to communicate about COVID-19. Objective: The aims of this study were to examine key themes and topics of English-language COVID-19–related tweets posted by individuals and to explore the trends and variations in how the COVID-19–related tweets, key topics, and associated sentiments changed over a period of time from before to after the disease was declared a pandemic. Methods: Building on the emergent stream of studies examining COVID-19–related tweets in English, we performed a temporal assessment covering the time period from January 1 to May 9, 2020, and examined variations in tweet topics and sentiment scores to uncover key trends. Combining data from two publicly available COVID-19 tweet data sets with those obtained in our own search, we compiled a data set of 13.9 million English-language COVID-19–related tweets posted by individuals. We use guided latent Dirichlet allocation (LDA) to infer themes and topics underlying the tweets, and we used VADER (Valence Aware Dictionary and sEntiment Reasoner) sentiment analysis to compute sentiment scores and examine weekly trends for 17 weeks. Results: Topic modeling yielded 26 topics, which were grouped into 10 broader themes underlying the COVID-19–related tweets. Of the 13,937,906 examined tweets, 2,858,316 (20.51%) were about the impact of COVID-19 on the economy and markets, followed by spread and growth in cases (2,154,065, 15.45%), treatment and recovery (1,831,339, 13.14%), impact on the health care sector (1,588,499, 11.40%), and governments response (1,559,591, 11.19%). Average compound sentiment scores were found to be negative throughout the examined time period for the topics of spread and growth of cases, symptoms, racism, source of the outbreak, and political impact of COVID-19. In contrast, we saw a reversal of sentiments from negative to positive for prevention, impact on the economy and markets, government response, impact on the health care industry, and treatment and recovery. Conclusions: Identification of dominant themes, topics, sentiments, and changing trends in tweets about the COVID-19 pandemic can help governments, health care agencies, and policy makers frame appropriate responses to prevent and control the spread of the pandemic.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The unpredictability of the coronavirus due to the lack of complete knowledge on transmission and treatment motivates people to stay updated with the latest information (Abd-Alrazaq et al., 2020; Chandrasekaran et al., 2020).”
From Understanding user responses to the COVID-19 pandemic on Twitter from a terror management theory perspective: Cultural differences among the US, UK and India (2022) · cites this paper as Chandrasekaran et al., 2020
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“most research has been conducted from an infoveillance perspective, thus limiting our understanding to health-related responses, such as the origin of the novel coronavirus, preventive measures, and other public knowledge about the virus (Abd-Alrazaq et al., 2020; Boon-Itt et al., 2020; Chandrasekaran et al., 2020; Xue et al., 2020).”
From Understanding user responses to the COVID-19 pandemic on Twitter from a terror management theory perspective: Cultural differences among the US, UK and India (2022) · cites this paper as Chandrasekaran et al., 2020
Experimental — accuracy not yet measured
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
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
VADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087
Pandemics in the Age of Twitter: Content Analysis of Tweets during the 2009 H1N1 Outbreak
Chew, C., & Eysenbach, G. (2010) · PLoS ONE · doi:10.1371/journal.pone.0014118 · Cited by 1,614
http://ljournal.ru/wp-content/uploads/2016/08/d-2016-154.pdf
(2016) · ljournal eBooks · doi:10.18411/d-2016-154 · Cited by 1,178
Top concerns of tweeters during the COVID-19 pandemic: Infoveillance study
Abd-Alrazaq, A., Alhuwail, D., Househ, M., Hamdi, M., & Shah, Z. (2020) · Journal of Medical Internet Research · doi:10.2196/19016 · Cited by 774 · cited 2×
“With a large corpus of texts, the unsupervised nature of LDA can result in the generation of topics that are neither meaningful nor effective, requiring human intervention and multiple iterations [10].”
BackgroundChen, E., Lerman, K., & Ferrara, E. (2020) · JMIR Public Health and Surveillance · doi:10.2196/19273 · Cited by 762
Global Sentiments Surrounding the COVID-19 Pandemic on Twitter: Analysis of Twitter Trends
Lwin, M. O., Lu, J., Sheldenkar, A., Schulz, P. J., Shin, W., Gupta, R., & Yang, Y. (2020) · JMIR Public Health and Surveillance · doi:10.2196/19447 · Cited by 443
World leaders' usage of twitter in response to the COVID-19 pandemic: A content analysis
Rufai, S. R., & Bunce, C. (2020) · Journal of Public Health · doi:10.1093/pubmed/fdaa049 · Cited by 308 · cited 1×
“2020 203 viral tweets by 8 G7b world leaders Twitter Rufai and Bunce, 2020 [17]”
BackgroundLiu, Q., Zheng, Z., Zheng, J., Chen, Q., Liu, G., Chen, S., Chu, B., Zhu, H., Akinwunmi, B., Huang, J., et al. (2020) · Journal of Medical Internet Research · doi:10.2196/19118 · Cited by 288
Budhwani, H., & Sun, R. (2020) · Journal of Medical Internet Research · doi:10.2196/19301 · Cited by 280
Research works printed but not linked: 3
- Srinivasa-Desikan, B, 2018, Natural Language Processing and Computational Linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras
- Blei, D, 2003, J Mach Learn Res, 3, 993
- JagarlamudiJIiiHUdupaRIncorporating Lexical Priors into Topic Models201213th Conference of the European Chapter of the Association for Computational LinguisticsApril 23-27, 2012Avignon, France
Cited by
Items 201–214 of 214
Classification of supervised deep learning models for COVID-19 tweets sentiment analysis
alkhafaji, R. M., Kadhim, S. A., Sameer, H. A., & muslim, D. H. A. (2024) · GSC Advanced Research and Reviews · doi:10.30574/gscarr.2024.20.1.0268
Hankar, M., Kasri, M., Mzili, T., & Beni‐Hssane, A. (2024) · Research Square · doi:10.21203/rs.3.rs-5435843/v1
Emotions Divergence in Online Social Network During Pandemic: A Sentiment Analysis
Danuri, M. S. N. M., Rashidia, N. H., & Rahman, R. A. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4613-5_14
Bibliometric Insights into the Infodemic: Global Research Trends and Policy Responses (Preprint)Preprint
Ren, S., Zhang, L., Liu, Y., Wang, S., & Feng, X. (2025) · doi:10.2196/preprints.76378
Hacia una visión integral del bienestar digital de los seniors españoles.
Cabrera-Nocito, V., Ibar-Alonso, R., & Navío-Marco, J. (2025) · Anduli · doi:10.12795/anduli.2025.i28.06 · Cited by 1
Blame and epidemics: A methodological commentary on qualitative social media research
Roy, M., Pinault, E., Moreau, N., & Atlani-Duault, L. (2025) · SSM - Qualitative Research in Health · doi:10.1016/j.ssmqr.2025.100661 · Cited by 1
Wang, J., Aaron, A., Baidya, A., Chan, C., Wetzler, E., Savage, K., Joseph, M., & Kang, Y. (2021) · Figshare · doi:10.6084/m9.figshare.16935911
Additional file 1 of Analyzing user ideologies and shared news during the 2019 argentinian elections
del Pozo, S. M., Pinto, S., Serafino, M., Garcia, L., Makse, H. A., & Balenzuela, P. (2024) · Figshare · doi:10.6084/m9.figshare.26758808
Guigma, T. A., & Brooks, I. S. (2026) · medRxiv · doi:10.64898/2026.01.18.26344365
From discourse to dynamics: the CUE-ESI framework for modeling community concern
Gupta, D., & Chakraverty, S. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01024-z
Lyu, Z., Takikawa, H., & Shimokubo, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5512197
The digital pulse of disaster: tracking public health needs via X during 2023 Türkiye earthquakes
Esen, M. F., Yılmaz, F. K., & Karakuş, S. (2026) · BMC Public Health · doi:10.1186/s12889-026-27649-x · Cited by 1
Partisan and Geographic Variation in Emotional Responses to COVID-19 Vaccination on Social Media
Jaidka, K., Wu, Y., Rani, A., Kuru, O., Jamalova, R., Sherman, G., & Guntuku, S. C. (2026) · JAMA Network Open · doi:10.1001/jamanetworkopen.2026.15409
Guadalupe, G. C. A., Gamboa-Tama, J. E., Mollineda, K. M., & Peralta-Gamboa, D. A. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1789164
Metadata
- Authors
- Chandrasekaran, R., Mehta, V., Valkunde, T., & Moustakas, E.
- Affiliations
- University of Illinois Chicago (US)
- Middlesex University Dubai (AE)
- Corresponding author
- Chandrasekaran, Ranganathan
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2020-10-23
- Volume
- 22
- Issue
- 10
- Pages
- e22624
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC7588259
- OpenAlex
- W3088268279
- Cited by
- 214
- References
- 27
- Citations by year
- 2026: 6 · 2025: 21 · 2024: 27 · 2023: 48 · 2022: 54 · 2021: 53 · 2020: 5
- FWCI
- 15.71
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- other-oa
- Locations
- Journal of Medical Internet Research (publishedVersion, other-oa)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Middlesex University Research Repository (Middlesex University Of London) (acceptedVersion)
- 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, Twitter, social media, public sentiment, temporal trends, infoveillance, economic impact, government response, health sector, racism, prevention, public health communication
- MeSH terms
- Betacoronavirus, COVID-19, SARS-CoV-2, Disease Outbreaks, Humans, Health Knowledge, Attitudes, Practice, Pneumonia, Viral, Coronavirus Infections, 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.