Project Stop-The-Clock Data extraction from unstructured information sources

Extraction and analysis of unstructured data and natural language


Stop the clock is a project whose objective is the extraction and analysis of unstructured information, written in natural language, from the EFSA website where the information is published in PDF (reports, minutes…), HTML and text files, automating structured, storable, understandable and analysable data collection processes.


Stop the clock has been created for the following purposes:

  • To facilitate and automate the collection of information from external sources with documents written in natural language, such as minutes and documentation with recommendations and requests on various products.
  • To control the response time from the publication of results in the external source and the response by the company or institution to the official body, reducing analysis times of all published reports and controlling the response times of the bodies involved.

With this work cycle, meetings, publication, approval and monitoring of products are controlled through statistical graphs, which help to understand the response times of both organisations. In this way, communication and management between them can be improved, making it possible to adjust the mechanisms to reduce the time spent on decision-making, since each agency will have a time clock that will record its responses and actions.

This global vision facilitates the understanding and access to information that otherwise takes months of reviewing minutes and web publications.

Duration: 2018-2021

Funding type: Private/industrial