Learning about text and data mining: The future of Open Science

The volume of digital data is doubling every two years. In the world of science, the cumulative total of articles published since 1665 is estimated to be more than 50 million. There is a wealth of knowledge hidden in this huge amount of articles, but reading and analysing all of them manually is not humanly possible. Text and data mining (TDM) can provide a solution. It can process millions of texts quickly and reveal patterns and trends that can lead to new discoveries in various fields, for example in research analytics, medicine, agriculture and social sciences. The European project OpenMinTeD [http://openminted.eu/] helps to solve these problems with a new platform on text and data mining