Text, data and link-mining in digital libraries: looking for the heritage gold

With the availability of new massive digital collections, innovative ways of exploring library data are emerging. Researchers are starting to investigate the use of powerful analysis tools that go beyond what the human eye can see, beyond what the human mind can process. Text and data mining techniques offer new opportunities for new types of research. Since a few years now, the BnF has seen its digital collections driving the interests of the early-adopters of new data management tools. These digital studies may be at the core of our users’ practice in the future; they may become instrumental in defining what a national library is. That’s why in 2016, the BnF started within its 4-year internal research programme a new project called CORPUS, aimed at designing a future service for providing access to digital corpora for researchers.