Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Sep;27(39):2200177.
doi: 10.2807/1560-7917.ES.2022.27.39.2200177.

Epitweetr: Early warning of public health threats using Twitter data

Laura Espinosa  1 , Ariana Wijermans  1 , Francisco Orchard  2 , Michael Höhle  3 , Thomas Czernichow  2   4 , Pietro Coletti  5 , Lisa Hermans  5 , Christel Faes  5 , Esther Kissling  2 , Thomas Mollet  1   6
Affiliations

Epitweetr: Early warning of public health threats using Twitter data

Laura Espinosa et al. Euro Surveill. 2022 Sep.

Erratum in

  • Erratum for Euro Surveill. 2022;27(39).
    Eurosurveillance editorial team. Eurosurveillance editorial team. Euro Surveill. 2022 Nov;27(44):221103e2. doi: 10.2807/1560-7917.ES.2022.27.44.221103e2. Euro Surveill. 2022. PMID: 36330822 Free PMC article. No abstract available.

Abstract

BackgroundThe European Centre for Disease Prevention and Control (ECDC) systematically collates information from sources to rapidly detect early public health threats. The lack of a freely available, customisable and automated early warning tool using data from Twitter prompted the ECDC to develop epitweetr, which collects, geolocates and aggregates tweets generating signals and email alerts.AimThis study aims to compare the performance of epitweetr to manually monitoring tweets for the purpose of early detecting public health threats.MethodsWe calculated the general and specific positive predictive value (PPV) of signals generated by epitweetr between 19 October and 30 November 2020. Sensitivity, specificity, timeliness and accuracy and performance of tweet geolocation and signal detection algorithms obtained from epitweetr and the manual monitoring of 1,200 tweets were compared.ResultsThe epitweetr geolocation algorithm had an accuracy of 30.1% at national, and 25.9% at subnational levels. The signal detection algorithm had 3.0% general PPV and 74.6% specific PPV. Compared to manual monitoring, epitweetr had greater sensitivity (47.9% and 78.6%, respectively), and reduced PPV (97.9% and 74.6%, respectively). Median validation time difference between 16 common events detected by epitweetr and manual monitoring was -48.6 hours (IQR: -102.8 to -23.7).ConclusionEpitweetr has shown sufficient performance as an early warning tool for public health threats using Twitter data. Since epitweetr is a free, open-source tool with configurable settings and a strong automated component, it is expected to increase in usability and usefulness to public health experts.

Keywords: Twitter; early warning; epidemic intelligence; machine learning; public health.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: None declared.

Figures

Figure 1
Figure 1
The epitweetr pipeline from installation to email alerts
Figure 2
Figure 2
Epitweetr dashboard
Figure 3
Figure 3
Differences in the validation time of common events between epitweetr and manual monitoring of tweets, 19 October–30 November 2020
See this image and copyright information in PMC

References

    1. Decision No. 1082/2013/EU of the European Parliament and of the Council of 22 October 2013 on serious cross-border threats to health and repealing Decision No 2119/98/EC. Luxembourg: Official Journal of the European Union; 5 Nov 2013. Available from: https://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:32013D1082...
    1. European Centre for Disease Prevention and Control (ECDC). Communicable disease threats to public health in the European Union - Annual epidemiological report for 2019. Stockholm: ECDC; 2020. Available from: https://www.ecdc.europa.eu/en/publications-data/communicable-disease-thr...
    1. European Centre for Disease Prevention and Control (ECDC). Sources - Worldwide data on COVID-19. Stockholm: ECDC; 2020. Available from: https://www.ecdc.europa.eu/en/publications-data/sources-worldwide-data-c...
    1. Li C, Chen LJ, Chen X, Zhang M, Pang CP, Chen H. Retrospective analysis of the possibility of predicting the COVID-19 outbreak from Internet searches and social media data, China, 2020. Euro Surveill. 2020;25(10). .10.2807/1560-7917.ES.2020.25.10.2000199 - DOI - PMC - PubMed
    1. Rocklöv J, Tozan Y, Ramadona A, Sewe MO, Sudre B, Garrido J, et al. Using Big Data to Monitor the Introduction and Spread of Chikungunya, Europe, 2017. Emerg Infect Dis. 2019;25(6):1041-9. .10.3201/eid2506.180138 - DOI - PMC - PubMed

LinkOut - more resources