Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study
Open accessPublished version of a preprint
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Background: Coronavirus disease (COVID-19) has affected more than 200 countries and territories worldwide. This disease poses an extraordinary challenge for public health systems because screening and surveillance capacity is often severely limited, especially during the beginning of the outbreak; this can fuel the outbreak, as many patients can unknowingly infect other people. Objective: The aim of this study was to collect and analyze posts related to COVID-19 on Weibo, a popular Twitter-like social media site in China. To our knowledge, this infoveillance study employs the largest, most comprehensive, and most fine-grained social media data to date to predict COVID-19 case counts in mainland China. Methods: We built a Weibo user pool of 250 million people, approximately half the entire monthly active Weibo user population. Using a comprehensive list of 167 keywords, we retrieved and analyzed around 15 million COVID-19–related posts from our user pool from November 1, 2019 to March 31, 2020. We developed a machine learning classifier to identify “sick posts,” in which users report their own or other people’s symptoms and diagnoses related to COVID-19. Using officially reported case counts as the outcome, we then estimated the Granger causality of sick posts and other COVID-19 posts on daily case counts. For a subset of geotagged posts (3.10% of all retrieved posts), we also ran separate predictive models for Hubei province, the epicenter of the initial outbreak, and the rest of mainland China. Results: We found that reports of symptoms and diagnosis of COVID-19 significantly predicted daily case counts up to 14 days ahead of official statistics, whereas other COVID-19 posts did not have similar predictive power. For the subset of geotagged posts, we found that the predictive pattern held true for both Hubei province and the rest of mainland China regardless of the unequal distribution of health care resources and the outbreak timeline. Conclusions: Public social media data can be usefully harnessed to predict infection cases and inform timely responses. Researchers and disease control agencies should pay close attention to the social media infosphere regarding COVID-19. In addition to monitoring overall search and posting activities, leveraging machine learning approaches and theoretical understanding of information sharing behaviors is a promising approach to identify true disease signals and improve the effectiveness of infoveillance.
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.
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
A new coronavirus associated with human respiratory disease in China
Wu, F., Zhao, S., Yu, B., Chen, Y.-M., Wang, W., Song, Z.-G., Hu, Y., Tao, Z.-W., Tian, J.-H., Pei, Y.-Y., et al. (2020) · Nature · doi:10.1038/s41586-020-2008-3 · Cited by 11,688 · cited 1×
“Since the outbreak of coronavirus disease (COVID-19) in December 2019 in Wuhan, Hubei Province, China [1,2], the novel coronavirus has affected more than 200 countries and territories worldwide.”
BackgroundInvestigating Causal Relations by Econometric Models and Cross-Spectral Methods
Granger, C. W. J. (2010) · Essays in Econometrics · doi:10.1017/cbo9780511753978.002 · Cited by 4,762
Wu, J. T., Leung, K., & Leung, G. M. (2020) · The Lancet · doi:10.1016/s0140-6736(20)30260-9 · Cited by 4,389
The Parable of Google Flu: Traps in Big Data Analysis
Lazer, D., Kennedy, R., King, G., & Vespignani, A. (2014) · Science · doi:10.1126/science.1248506 · Cited by 2,523
Eysenbach, G. (2009) · Journal of Medical Internet Research · doi:10.2196/jmir.1157 · Cited by 1,351 · cited 2×
“Specifically, data based on internet searches and social media activities can nowcast and forecast disease prevalence as a supplement to conventional surveillance methods for various infectious diseases [5-7,9-14].”
BackgroundLi, C., Chen, L. J., Chen, X., Zhang, M., Pang, C. P., & Chen, H. (2020) · Eurosurveillance · doi:10.2807/1560-7917.es.2020.25.10.2000199 · Cited by 313
Research works printed but not linked: 30
- 10.1016/s0140-6736(20)30183-5 · DOI · Paper page
- 10.1146/annurev-soc-073117-041421 · DOI · Paper page
- 10.1371/journal.pone.0014118 · DOI
- 10.1146/annurev-publhealth-040119-094402 · DOI · Paper page
- 10.2196/13680 · DOI · Paper page
- 10.1371/journal.pone.0139701 · DOI · Paper page
- 10.1007/s00779-015-0877-5 · DOI
- 10.1186/2049-9957-2-31 · DOI
- 10.1371/journal.pone.0083672 · DOI · Paper page
- 10.2196/jmir.5585 · DOI
- 10.1093/cid/cir883 · DOI · Paper page
- 10.1371/journal.pntd.0005295 · DOI · Paper page
- 10.1109/tcss.2020.2980007 · DOI · Paper page
- 10.1017/dmp.2020.68 · DOI
- 10.2196/18700 · DOI · Paper page
- 10.2196/18825 · DOI · Paper page
- 10.2196/19087 · DOI
- 10.1080/08838151.2019.1653104 · DOI
- 10.1177/209660831900200406 · doi:10.1177/209660831900200406
- 10.1177/1077699015607338 · DOI · Paper page
- HuYHuangHChenAMaoXLarXiv202005212020-05-26Weibo-COV: A Large-Scale COVID-19 Social Media Dataset from Weibohttps://arxiv.org/abs/2005.09174
- 10.1016/S2589-7500(20)30026-1 · DOI · Paper page
- 10.2307/1912791 · DOI · Paper page
- 10.1080/01621459.1975.10480264 · DOI · Paper page
- Box-Steffensmeier, J, 2014, Time Series Analysis for the Social Sciences, 10.1017/CBO9781139025287 · DOI · Paper page
- 10.1016/s2589-7500(20)30059-5 · DOI · Paper page
- 10.3390/ijerph17072309 · DOI · Paper page
- 10.1016/s2589-7500(20)30055-8 · DOI
- 10.1080/13669877.2020.1756380 · DOI
- 10.1016/S1473-3099(20)30144-4 · DOI · Paper page
Cited by
Social Media Use for Health Purposes: Systematic Review
Chen, J., & Wang, Y. (2021) · Journal of Medical Internet Research · doi:10.2196/17917 · Cited by 1,073
Public perception of the COVID-19 pandemic on Twitter: Sentiment analysis and topic modeling study
Boon-Itt, S., & Skunkan, Y. (2020) · JMIR Public Health and Surveillance · doi:10.2196/21978 · Cited by 486
“Taking research published in 2020 as examples, Shen et al [12] studied mentions of symptoms and diseases on social media to predict COVID-19 case counts, and Huang et al [13] analyzed social media posts to study the characteristics of COVID-19 patients in China.”
MethodSocial media and health care, part I: literature review of social media use by health care providers
Farsi, D. (2021) · Journal of Medical Internet Research · doi:10.2196/23205 · Cited by 299
Topics, trends, and sentiments of tweets about the COVID-19 pandemic: Temporal infoveillance study
Chandrasekaran, R., Mehta, V., Valkunde, T., & Moustakas, E. (2020) · Journal of Medical Internet Research · doi:10.2196/22624 · Cited by 214
Adly, A. S., Adly, A. S., & Adly, M. S. (2020) · Journal of Medical Internet Research · doi:10.2196/19104 · Cited by 138
Metadata
- Authors
- Shen, C., Chen, A., Luo, C., Zhang, J., Feng, B., & Liao, W.
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2020-05-28
- Volume
- 22
- Issue
- 5
- Pages
- e19421
- ISSN
- 1438-8871 (ISSN-L)
- OpenAlex
- W3027908495
- Cited by
- 127
- References
- 6
- FWCI
- 15.51
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study. https://app.cochat.ai/papers/10.2196/19421
- The paper
- Shen, C., Chen, A., Luo, C., Zhang, J., Feng, B., & Liao, W. (2020). Using Reports of Symptoms and Diagnoses on Social Media to Predict COVID-19 Case Counts in Mainland China: Observational Infoveillance Study. Journal of Medical Internet Research. https://doi.org/10.2196/19421
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.