Twitter Discussions and Emotions About the COVID-19 Pandemic: Machine Learning Approach
Open accessPublished version of a preprint
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
BACKGROUND: It is important to measure the public response to the COVID-19 pandemic. Twitter is an important data source for infodemiology studies involving public response monitoring. OBJECTIVE: The objective of this study is to examine COVID-19-related discussions, concerns, and sentiments using tweets posted by Twitter users. METHODS: We analyzed 4 million Twitter messages related to the COVID-19 pandemic using a list of 20 hashtags (eg, "coronavirus," "COVID-19," "quarantine") from March 7 to April 21, 2020. We used a machine learning approach, Latent Dirichlet Allocation (LDA), to identify popular unigrams and bigrams, salient topics and themes, and sentiments in the collected tweets. RESULTS: Popular unigrams included "virus," "lockdown," and "quarantine." Popular bigrams included "COVID-19," "stay home," "corona virus," "social distancing," and "new cases." We identified 13 discussion topics and categorized them into 5 different themes: (1) public health measures to slow the spread of COVID-19, (2) social stigma associated with COVID-19, (3) COVID-19 news, cases, and deaths, (4) COVID-19 in the United States, and (5) COVID-19 in the rest of the world. Across all identified topics, the dominant sentiments for the spread of COVID-19 were anticipation that measures can be taken, followed by mixed feelings of trust, anger, and fear related to different topics. The public tweets revealed a significant feeling of fear when people discussed new COVID-19 cases and deaths compared to other topics. CONCLUSIONS: This study showed that Twitter data and machine learning approaches can be leveraged for an infodemiology study, enabling research into evolving public discussions and sentiments during the COVID-19 pandemic. As the situation rapidly evolves, several topics are consistently dominant on Twitter, such as confirmed cases and death rates, preventive measures, health authorities and government policies, COVID-19 stigma, and negative psychological reactions (eg, fear). Real-time monitoring and assessment of Twitter discussions and concerns could provide useful data for public health emergency responses and planning. Pandemic-related fear, stigma, and mental health concerns are already evident and may continue to influence public trust when a second wave of COVID-19 occurs or there is a new surge of the current 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
Figures






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
“First, most were based on tweets collected in the early stages of the pandemic, which were analyzed from an infoveillance perspective, thereby limiting their analyses to health-related responses (e.g., Abd-Alrazaq et al., 2020; Boon-Itt 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 Xue 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
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
S., N. L. (2017) · doi:10.1177/1609406917733847 · Cited by 14,051
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
An Introduction to Statistical Learning
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013) · Springer Texts in Statistics · doi:10.1007/978-1-4614-7138-7 · Cited by 12,106
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
The COVID-19 social media infodemic
Cinelli, M., Quattrociocchi, W., Galeazzi, A., Valensise, C. M., Brugnoli, E., Schmidt, A. L., Zola, P., Zollo, F., & Scala, A. (2020) · Scientific Reports · doi:10.1038/s41598-020-73510-5 · Cited by 2,313 · cited 1×
“Existing studies have indicated the feasibility of using LDA to identify the patterns and themes of tweets related to COVID-19 [11,22].”
BackgroundExploring the Space of Topic Coherence Measures
Röder, M., Both, A., & Hinneburg, A. (2015) · Proceedings of the Eighth ACM International Conference on Web Search and Data Mining · doi:10.1145/2684822.2685324 · Cited by 2,224
Li, S., Wang, Y., Xue, J., Zhao, N., & Zhu, T. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17062032 · Cited by 1,835 · cited 2×
“Comparison With Prior Work Our findings are consistent with previous studies using social media data to assess the public health responses and sentiments related to COVID-19, and suggest that public attention has been focusing on the following topics since January 2020: (1) the confirmed cases and death rates [11,18,3…”
BackgroundResultSelf-citationPandemics 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
Research works printed but not linked: 2
- Blei, D, 2003, Journal of Machine Learning Research March, 3, 993
- Kaila, RP, 2020, International Journal of Advanced Research in Engineering and Technology, 11, 128
Cited by
Items 301–368 of 368
The Performance of Cryptocurrencies under a Sentiment Analysis Approach in the Time of COVID-19Preprint
Vasileiou, E., & Koutrakos, P. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3987604
Huang, H., & Qiu, Y. (2021) · doi:10.2196/preprints.30136
Ke, S. Y., Tass, E. S., Barnes, M., Hanson, C. L., & Snell, Q. O. (2022) · doi:10.2196/preprints.37861
COVID-19 Vaccination Decision-Making Approach and the Sentiments of Indian Citizens
Chandel, S., & Gochhait, S. (2022) · International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa54658.2022.9765147
Pragmatics Analysis on Anger Expression in #IndonesiaTerserah on Twitter
Ulrikayanti, G. F. (2022) · Indonesian Journal of English Language Studies (IJELS) · doi:10.24071/ijels.v8i1.3886
Analysis of Twitter Conversation on COVID-19 Pandemic in Africa 2019-2020
Sanni, S. A., Rajabu, N., Yusuf, A. O., Mathabela, N. N., & Alamu, L. K. (2021) · Journal of Health Promotion and Behavior · doi:10.26911/thejhpb.2021.06.04.02
Jiang, H., Castellanos, A., Castillo, A., Gomes, P. J., Li, J., & VanderMeer, D. E. (2022) · doi:10.2196/preprints.40676
How People Show Their Emotions towards COVID-19 on Twitter Platform
Zhao, L. (2022) · Advances in Journalism and Communication · doi:10.4236/ajc.2022.102012
Exploring Public Trust on State Initiatives During the COVID-19 Pandemic
Tan, A. S., Estuar, M. R. J. E., Co, N. A., Tan, H. C., Abao, R. P., & Aureus, J. P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-05061-9_46
Temas latentes asociados a la aparición de las nuevas variantes del coronavirus
Nasser, F. A. (2022) · Tendencias Sociales Revista de Sociología · doi:10.5944/ts.2022.34264
Coccia, M., Mele, M., & Magazzino, C. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4159474
Dhandapani, A., Balasubramaniam, A., Balasubramaniam, T., & Paul, A. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-19-2347-0_64
Using an ontology based big data architecture for predicting pandemic outbreak risk (Preprint)Preprint
Lau, A. S. M. (2022) · doi:10.2196/preprints.38983
Reliable Knowledge Discovery from Social Media Data in Health Crisis in Developing CountriesPreprint
Naseem, A., Hassan, M. T., Naseer, A., Rafique, M. A., & Jeon, M. (2022) · Research Square · doi:10.21203/rs.3.rs-1929938/v1
Managing The COVID-19 in Canada: Exploring Twitter Communication by Government and Health Officials
Chouikh, A., Medini, G., Mellouli, S., Straus, S. E., & Fahim, C. (2022) · Annual International Conference on Digital Government Research · doi:10.1145/3543434.3543485
Culture Measure, Twitter Sentiment and COVID-19 Statistics: A Regression Analysis (Preprint)Preprint
Wang, J., Bandera, C., & Yan, Z. (2022) · doi:10.2196/preprints.44506
The Soft Power of Understanding Social Media Dynamics: A Data-Driven Approach
Dzitac, D. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-24453-7_5
Kaur, J., Patel, S. K., Vasani, M., & Saini, J. R. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-9888-1_36
Guo, L., Wang, W., & Wu, Y. J. (2023) · SAGE Open · doi:10.1177/21582440231182060
Morgan, M., & Kulkarni, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35927-9_24
Performance of Cryptocurrencies Under a Sentiment Analysis Approach in the Time of COVID-19
Vasileiou, E., & Koutrakos, P. (2023) · Springer eBooks · doi:10.1007/978-3-031-36570-6_11
Alshanik, F., Khasawneh, R. A., Dalky, A. F., & Qawasmeh, E. (2023) · doi:10.2196/preprints.53434
The Governance of Artificial Intelligence in the “Autonomous City”
Cugurullo, F., Yiğitcanlar, T., Zhang, X., Del Casino, V., Gulsrud, N. M., & Barns, S. (2023) · Frontiers research topics · doi:10.3389/978-2-8325-3564-6
An Enhanced Emotion Classification Scheme for Twits Based on Deep Learning Approach
Sultan, L. R. (2023) · Revue d intelligence artificielle · doi:10.18280/ria.370512 · Cited by 2
Novel deep neural network based stress detection system
Jyothsna, R., Rohini, V., & Paulose, J. (2023) · AIP conference proceedings · doi:10.1063/5.0181900
Daulay, N. A., Ramadhan, R., & Suadaa, L. H. (2023) · Proceedings of The International Conference on Data Science and Official Statistics · doi:10.34123/icdsos.v2023i1.360
Gyftopoulos, S., Drosatos, G., Pecchia, L., Fico, G., & Kaldoudi, E. (2024) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-49062-0_86
Alba, C., & Abbasian, V. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4762168
A Review of Environmental Factors for an Ontology-Based Risk Analysis for Pandemic Spread
Cheung, L., Lau, A. S. M., Lam, K. F., & Ng, P. Y. (2024) · COVID · doi:10.3390/covid4040031
Parveen, S., Pereira, A. G., Orjuela, N. G., McHugh, P., Surendran, A., Vornhagen, H., & Vellinga, A. (2024) · doi:10.2196/preprints.59687
Curated and Asymmetric Exposure: A Case Study of Partisan Talk during COVID on Twitter
An, Z., Breuhaus, J., Niu, J., Sarıyüce, A. E., & Joseph, K. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31298 · Cited by 4
The Measurement of COVID-19 Vaccine Hesitancy
Rossouw, S., & Greyling, T. M. (2024) · Human well-being research and policy making · doi:10.1007/978-3-031-56529-8_7
Leveraging Entity Recognition for Automotive Customer Feedback Topic Modeling
Weber, L. J., Ramalingam, K. J., Liu, C., Beyer, M., & Zimmermann, A. P. (2024) · doi:10.1109/icnlp60986.2024.10692404
Infodemic Vs Pandemic: Covid-19 Crisis in Pakistan Due to Rumors on Twitter
Naveed, H., Younas, R., Haq, H. B. U., Abbas, S., Aslam, S., & Hassan, M. (2024) · Horizons of Information Technology and Engineering (HITE) · doi:10.1109/hite63532.2024.10777157
Less is More: Exploring Sampled Twitter Data Steams for Pandemic Surveillance and Monitoring
Xu, K., Wang, F., & Hoikka, M. (2024) · IEEE International Performance, Computing, and Communications Conference · doi:10.1109/ipccc59868.2024.10850027
Portuguese Emotion Detection Model Using BERTimbau Applied to COVID-19 News and Replies
Oliveira, F. B., & Sichman, J. S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-79032-4_19 · Cited by 2
Students' Readiness on Practical Learning in Mechanical Engineering Education: Post-Pandemic Survey
Hermansah, S., Sutiman, S., Mutohhari, F., & Khaharsyah, A. (2024) · JPI (Jurnal Pendidikan Indonesia) · doi:10.23887/jpiundiksha.v13i3.76249
Leveraging AraBERT for COVID-19 event monitoring on Arabic Twitter
Harrag, F., Touameur, O., & Zermani, M. (2025) · Performance Measurement and Metrics · doi:10.1108/pmm-12-2024-0059
Beyond dyadic interaction and shared experience: Rethinking social connections
Chou, F.-C. B., & Chen, P.-H. A. (2025) · The Psychology of learning and motivation/The psychology of learning and motivation · doi:10.1016/bs.plm.2025.03.002 · Cited by 2
Boland, K., Starke, C., Bensmann, F., Marcinkowski, F., & Dietze, S. (2025) · Journal of Medical Internet Research · doi:10.2196/63909 · Cited by 2
Artificial Intelligence during a Public Health Crisis: A Trend Analysis of COVID-19 Research
Choi, S., Lee, C. K., & Kim, D. (2025) · Korean Journal of Environmental Health Sciences · doi:10.5668/jehs.2025.51.3.109
Li, X., & Xiao, H. (2025) · Current Issues in Tourism · doi:10.1080/13683500.2025.2533521
Pourquoi les maladies liées au stress sont-elles si difficiles à diagnostiquer et comment y pallier
Khalili‐Mahani, N. (2023) · The Conversation · doi:10.64628/aap.vayhat5d6
Khalili‐Mahani, N. (2022) · The Conversation · doi:10.64628/aam.jdqe5a9pa
Ho, T. T. V. H. T. T. V., & Noh, M. (2025) · Health Services and Outcomes Research Methodology · doi:10.1007/s10742-025-00353-w · Cited by 1
Is this real life? – Exploring leadership communication on Twitter/X
Strauss, C., Harr, M. D., & Pieper, T. M. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2563661 · Cited by 3
Long COVID Times: An X/Twitter-Informed Rhythmanalysis of Pacing
Martin, S., & Uprichard, E. (2025) · Springer eBooks · doi:10.1007/978-981-96-9168-5_3 · Cited by 15
A multiclass graph neural network–based framework for predicting post engagement in social media
Arazzi, M., Cotogni, M., Nocera, A., Ursino, D., & Virgili, L. (2026) · Journal of Information Science · doi:10.1177/01655515251396879
Wang, T.-H., Wang, T.-C., Li, C. K., Hsu, L., Hou, S.-M., & Ruey-Shan, G. (2026) · Journal of the Formosan Medical Association · doi:10.1016/j.jfma.2026.01.012
Guigma, T. A., & Brooks, I. S. (2026) · medRxiv · doi:10.64898/2026.01.18.26344365
County Partisanship Affects Social Media Posting Behavior During a Pandemic
Smith, M., Chi, G., Yin, J., Bodovski, Y., & Sundar, S. S. (2026) · Social Media + Society · doi:10.1177/20563051261419387
Topic Modeling of Social Media Sleep Health Discourse Using BERTopic: A Study of Naver Blog Big Data
Song, J. (2026) · Journal of Health Informatics and Statistics · doi:10.21032/jhis.2026.51.1.12
Paolillo, R., Hilmar, T., & Sachweh, P. (2026) · European Politics and Society · doi:10.1080/23745118.2026.2645109
Gao, J., Windett, J. H., Radford, B. J., Ademu, L., & Racine, E. F. (2026) · doi:10.2196/preprints.96677
From Machine Learning to Transformers: A Comparative Study on Emotion Classification of Tweets
Zafar, B., Saeed, A., Kiran, H. M., Nasir, M., & Hameed, A. (2026) · VAWKUM Transactions on Computer Sciences · doi:10.21015/vtcs.v14i1.2236
Artificial Intelligence and Computation in the Social Sciences: A Paradigm Shift
Boyd, R. L., Srinivas, S., Phadke, S., Wilson, S. R., & Pasca, P. (2026) · Oxford University Press eBooks · doi:10.1093/9780197807309.003.0003
Unnikrishnan, R., Kamath, S., & Ananthanarayana, V. S. (2025) · Intelligent systems reference library · doi:10.1007/978-3-032-13497-4_4
Text‐Based Analysis of Twitter Data with Machine Learning Models
Malathy, N., Sharmila, G., Yuvarshini, R., & Lavanya, R. (2026) · doi:10.1002/9781394393060.ch7
Vial, V., & Richomme‐Huet, K. (2026) · Journal of Social Entrepreneurship · doi:10.1080/19420676.2026.2684658
Aotearoa on Twitter during COVID-19 lockdowns
Phillips, J. B. (2026) · Political Science · doi:10.1080/00323187.2026.2680880
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
Leveraging Social Media and Large Language Models for COVID-19 Forecasting
Liu, Y., Liu, H., & Cochran, J. T. (2026) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera69989.2026.11618672
Mattes, M., Arifi, D., & Resch, B. (2026) · Computational Urban Science · doi:10.1007/s43762-026-00293-2
Kharti, K., Lafraxo, M. A., Harifi, H., Erefai, O., Soulaymani, A., & Hami, H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-28573-7_22
Timing Matters: Contrasting Public Sentiment During Wuhan’s and Shanghai’s COVID-19 Lockdowns
Pei, X., Isoda, Y., Nakaya, T., & Sabel, C. E. (2026) · Journal of Disaster Research · doi:10.20965/jdr.2026.p1019
Mammalian H5N1 cases predict online discourse volume and emotion during the 2024–2025 H5N1 outbreakPreprint
Pria, L. D., Koebel, K. J., Nelson, A., & Ivanek, R. (2026) · Research Square · doi:10.21203/rs.3.rs-11270170/v1
Boateng, E. B., Frimpong, S., Sunindijo, R. Y., Hon, C. K. H., Wang, C., Coman, R. L., & Gopaldasani, V. (2026) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-18895
Metadata
- Authors
- Xue, J., Chen, J., Hu, R., Chen, C., Zheng, C., Su, Y., & Zhu, T.
- Affiliations
- University of Toronto (CA)
- University of Pittsburgh (US)
- Chinese Academy of Sciences (CN)
- Corresponding author
- Zhu, Tingshao
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2020-11-25
- Volume
- 22
- Issue
- 11
- Pages
- e20550
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC7690968
- OpenAlex
- W3096451393
- Cited by
- 369
- References
- 34
- Citations by year
- 2026: 22 · 2025: 26 · 2024: 41 · 2023: 83 · 2022: 99 · 2021: 92 · 2020: 6
- FWCI
- 27.50
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Institutional Repository of Institute of Psychology, Chinese Academy of Sciences (Institute of Psychology, Chinese Academy of Sciences) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- TSpace (University of Toronto) (submittedVersion, cc-by)
- Greater South Information System
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Communication › Communication and COVID-19 Impact
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- COVID-19 pandemic, Twitter, public sentiment, infodemiology, social media discourse, fear, COVID-19 stigma, public health measures, social distancing, quarantine, hashtags, topic modeling, latent Dirichlet allocation, public trust
- MeSH terms
- Machine Learning, COVID-19, SARS-CoV-2, Data Collection, Emotions, Humans, 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.