6 October 2016 1.00pm — 2.00pm
Centre for Digital Scholarship, Weston Library (Map)
Simon Baker, Jonathan Blaney, Marty Steer
Trying to classify historical texts using the BBIH Thesaurus
The Institute of Historical Research collates and classifies a large variety of material relating to History in UK Higher Education. With the rise of open access publishing and the proliferation of web resources, keeping up has become more and more difficult. Funding from the AHRC has allowed the IHR's digital team to explore ways of automatically classifying works based on features such as book blurbs, article abstracts, titles and metadata.
This talk will cover the challenges the AHRC-funded TOBIAS project has met in classifying this material, using the Royal Historical Society's fine-grained vocabulary of British and Irish history. Techniques the team is trying ranged from 'bag of words' string matching to machine learning.
This event is free but places are limited so please complete our booking form to reserve tickets in advance.Lectures and talks; Free events