The Europe Media Monitor (EMM) is a system developed at the Joint Research Centre which continuously monitors 17 000 web sites and processes about 450 000 publicly available pages every day in 80 languages.
The EMM system is a key testbed for scientific research at JRC. The high-volume stream of multilingual text articles enables research into multilingual natural language processing, and our research in text mining is investigating areas including multilingual topic mining, text classification, named entity recognition and the use of persuasion techniques in text. Over the years JRC has developed and tested different approaches to these challenges, integrating high quality and performant results into the system.
EMM also enables JRC research in many other domains, by providing scientists with timely information streams relevant to their research in a wide range of domains such as natural disasters, public health threats & food safety, conflict early warning, border security, crime or science and innovation.
These research activities mean that the JRC is also able to support the media monitoring activities of the European Institutions, capitalising on the funds spent on research to provide direct support to policy makers and communication officers.
To demonstrate the text and data mining research done in EMM, and to promote research collaborations, JRC runs a public website showing some of the results of EMM, such as the top news stories of the day.
Academia and researchers can contact the EMM team by writing to: JRC-EMM-INFO@ec.europa.eu
Latest knowledge
Originally published | 19 Dec 2022 | 25 May 2023 |
Knowledge service | Metadata | Text Mining |
Digital Europa Thesaurus (DET) | natural language processingmultilingualism |