ECDC launches new version of epitweetr, a tool for the early detection of public health threats using Twitter dataArchived

ECDC has launched a new version of epitweetr, the R-based tool that allows users to automatically monitor trends of tweets by time, place, and topic, with the aim of detecting public health threats early through signals, such as an unusual increase in the number of tweets. It is designed to support public health experts with the early detection of threats from infectious diseases and can be extended to all hazards and other fields of study by modifying the topics and keywords.

This new version launched in January 2022 includes:

• Improved data storage and management;
• Addition of Twitter API version 2;
• A new feature to facilitate data privacy compliance;
• Improved extraction of geolocation from the tweet text; and
• Automatic classification of signals detected using annotations from the user.

This new version of the epitweetr package also includes an interactive web application (based on the R package Shiny) with six pages:

1. Dashboard, where a user can visualise and explore tweets, and download the associated outputs and data;
2. Alerts, where you can view the current alerts and associated information, and train machine learning models for alert classification on user-defined categories;
3. Geotag evaluation, where you can evaluate the geolocation algorithm and provide annotations for improving its performance;
4. Data protection, where you can search, anonymise, and delete tweets from the epitweetr database to support data deletion requests;
5. Configuration, where you can change settings and check the status of the underlying processes; and
6. Troubleshooting, with automatic checks and hints for using epitweetr and all its functionalities.