Scientific Health Papers Text Mining Pilot

5 years ago

 

To fulfil the requirements of identification of concrete big data and open knowledge opportunities and requirements in public administrations stated by the ISA action 1.22, the execution of a proof of concept that showcases the use of big data in the EC research domain was needed. This was done in cooperation with DG RTD in order to prove the usefulness and policy benefit that big data can bring. The proof of concept shall demonstrate the use of text mining techniques used on large amounts of unstructured research health papers from several data sources as a means to identify areas of interest for an additional input to consider prior to launching calls for grants.

Attached for your information, the source code of the project is located in the "Rtd_Source_Code.zip" file, where you can find the software implementation of the project. The enclosed documents present information about every stage of the project, such as the Proof of concept (PoC), requirements, technological architecture and final report among others.