Monitoring the internet regularly is crucial for the global security community to detect emerging threats, such as public health outbreaks and various types of instability. By applying its core scientific competences in computer science and computational linguistics to massive datasets, the JRC develops open source intelligence and analysis systems that can automatically harvest and analyse a huge amount of multi-lingual information from internet-based sources. Linguistic Resources and Tools (multilingual software, parallel corpora, and more) developed by the JRC are available for download from the Language Technology Resources webpages.
Europe Media Monitor (EMM)
Europe Media Monitor (EMM) is a framework developed and maintained by the JRC for Open Source Information Monitoring and analysis. EMM and the applications built around it provide decision makers with timely evidence-based alerts to support humanitarian interventions, health crisis management and early warning in a number of security and crisis scenarios. EMM is a live media monitoring system which gathers around 220,000 news articles every day from over 7000 internet news websites from around the world in over 70 different languages. Updated every 10 minutes, it groups all news articles that focus on the same subject, and brings to the fore the most important stories unfolding in the news. EMM applies leading edge techniques in information mining on each article, automatically determining what is happening to whom and where by: classifying every received article according to a hierarchy of some 1000 classes (what); identifying People and Organisations (who) in the news; geo-locating each article (where); and sensing positive or negative tonality.
Medical Information System (MedSIsys)
Internet surveillance systems are routinely used for early event detection, alerting and tracking of emerging public health threats. The Medical Information System (MedSIsys), developed by the JRC, helps to rapidly identify potential threats to public health. Statistical modelling techniques help to distinguish topics that appear regularly in the news from those that are suddenly reported, meaning that advance warning can be given if a topic of concern arises.