The Library’s data collections are being included in a collaborative project, led by Edina at the University of Edinburgh, to build a text and data mining platform.
Aims of the project
This City Deal-funded collaborative project, led by Edina, will develop an intuitive, easy-to-use text and data mining pilot service, based work by Professor Melissa Terras and Dr Rosa Filgueira on the Defoe tool at University College London (UCL).
The project will produce a text and data mining platform with an intuitive visual interface, to provide a service for students, researchers and businesses supported by data skills training. This will enable new audiences to use text and data mining techniques with a range of documents hosted by the platform.
Outputs of this first phase include:
– A pilot text and data mining service, based on Defoe technology, ready for test and learn adoption
-A recommendations report describing text and data mining skills, dataset and service requirements across the City Deal region
-A catalogue of exemplar datasets and a clear ingest process for new datasets
-A report clarifying legal issues and proposing appropriate frameworks for copyright
-Exemplar datasets and data learning materials
National Library of Scotland data
Digitised material on the Data Foundry will be used with the platform, with initial datasets including Encyclopaedia Britannica and Gazetteers of Scotland.
By participating in this project, the Library is enabling audiences without advanced technical skills to carry out large-scale analysis of the collections using text and data mining techniques.
Find out more
More information about the text and data mining platform: City region deal text and data mining