At Learning on Screen, we are exploring the potential in our archive of over 2.4 million television and radio broadcasts as a dataset to train algorithms – the BoB archive – available for research purposes, particularly in the field of Artificial Intelligence.
BoB is Learning on Screen’s on demand TV and radio service for education. The BoB archive includes over 2.4 million broadcasts dating back as far as the 1950s and accompanied by a significant quantity of metadata. For example, each show on BoB includes details about cast and crew as well as identifiers for search purposes, and a large quantity of TV material comes with a transcript. BoB is also connected to Learning on Screen’s TRILT database. This offers additional metadata and enhanced search features.
As such, we believe our unique archive has great potential as a dataset to train algorithms, for example as a self-updating source of natural language.
Studying diversity and representation on screen in the UK with computer vision methods
Learning on Screen is currently conducting a pilot project in collaboration with Nesta to investigate the challenges and opportunities related to using the BoB archive to apply machine learning to answer different research queries. The project – led by Raphael Leung and Cath Sleeman (Nesta) – will analyse a sample of the BoB archive to explore how computer vision can be used to study diversity and representation on British TV, with a focus on gender inequality.
AI and Audiovisual Archives
On 14th February 2020, Learning on Screen organised the event AI and Audiovisual Archives, aimed at identifying challenges as well as the endless opportunities related to using audiovisual archives to develop artificial intelligence-powered tools for education and research. The event brought together leading practitioners and academics from various fields, including computer science, media studies and law.
The event programme included discussions and panel presentations from Cath Sleeman (Nesta), Max Cleary (Digital Catapult), and Thomas Margoni (CREATe, University of Glasgow). You can download the slides from the three presentations below:
Cath Sleeman – Head of Data Visualisation at Nesta – Measuring gender imbalances in the creative industries
Max Cleary – Partnerships Lead – AI, Immersive & 5G at the Digital Catapult – 3_Max-Cleary_Digital-Catapult> Industry trends in AI, video and archive
Thomas Margoni – Senior Lecturer in Intellectual Property and Internet Law at CREATe, University of Glasgow – AI, machine learning and the role of copyright in protecting non personal “data”.
You can access a CREATe report of the event here.