Monge: Geographic Monitor of Diseases

Resumen

Monge is a prototype of a geographic monitor of diseases, based on tweets. After the recovering phase of tweets, located in different Spanish cities, these tweets are processed and filtered with techniques and tools of Human Language Technologies. Tweets are filtered with three criteria: location, language (Spanish and Catalan) and bag of words of diseases (generated using synonyms of WordReference and embeddings). The processed information is presented in an interactive way allowing to predict possible epidemic outbreaks of different diseases (e.g. u, asthma). This demo could be very useful because the Centers for Disease Control and Prevention take between 1-2 weeks from the moment the patient is diagnosed until the data is available, while with this prototype a real-time monitoring of diseases is offered.