Fouille de données

« BBC Research and Development has launched a five-year research partnership with eight UK Universities, including the University of Manchester, to unlock the potential of data in the media. As part of the lauch event on 19th October 2017, NaCTeM presented semantic search. (…) »

« The aim of this guide is to make a start towards exposing the breadth of content (mostly library-subscribed) that may be of potential exploitation by Cambridge researchers wanting to use the techniques of text and data mining in their research. The guide summarizes the main points in the

« Text and data mining – using algorithms to analyse content in ways that would be impossible for humans – is shaping up to be a vital research tool of the 21st century. But Europe lags behind other parts of the world in adopting these new technologies. The FutureTDM project has…

« L’Inist partenaire du projet VISA TM

La création d’une offre en fouille de texte et de données – TDM (text and data mining) à destination des chercheurs s’avère prépondérante dans le contexte actuel de la Science Ouverte et plus particulièrement de la loi pour une République Numérique.

Conduit sous l’égide…

« L’extraction de textes et de données (Text and Data Mining), le traitement automatique ou la fouille de grandes quantités d’articles scientifiques et de jeux de données, est une pratique essentielle pour les chercheurs et les chercheuses contemporains. Certains éditeurs et éditrices contestent la légitimité de cette activité et le sujet…

« This report examines how the University Libraries at Virginia Tech have supported text and data mining in the past, and how academic libraries in general are providing support for it. The report looks at licensing content for TDM as well as legal and technical aspects. The report concludes with recommendations…

« Throughout the FutureTDM project, we have published a range of awareness sheets that cover different factors that have an impact on TDM uptake. With input coming from our expert reports, interviews and discussions through the Knowledge Café events, these sheets raise awareness of outcomes of high interest to people who work in…

« Presentation of Text-mining methods used for information extraction in plant scientific papers.

Part 1: Context

Part 2: From Text to Words

Part 3: From words to entity recognition

Part 4: Entity categorization

« FutureTDM Knowledge Base showcases structured collections of resources on Text and Data Mining (TDM) that has been gathered throughout the FutureTDM project phase. The collections encompass experts as projects or organisations focusing on TDM, as well as technologies and resources that are useful for TDM practitioners (i.e. TDM methods and TDM tools).…

« The Science and Technology Resources on the Internet column in the Spring 2017 issue of Issues in Science and Technology Librarianship includes a webliography of text mining resources.

This useful resource was compiled and written by Kristen Cooper, a librarian at the award-winning University of Minnesota…