Data - �鶹Լ�� R&D

White Paper WHP 409: Usage patterns in on-demand programmes after broadcast

Michael Armstrong

Selecting a programme from �鶹Լ�� iPlayer or �鶹Լ�� Sounds, do you consume it all the way through or skip to the highlights? It may depend on the type of programme......

White paper published Nov 2023

Responsible innovation and society

Data and technology affect all aspects of the �鶹Լ��, from our editorial operations and outputs to how audiences can discover and access our services and content. The �鶹Լ�� needs to...

Project

Addressing the cold start problem in recommender systems

�鶹Լ�� iPlayer has a constant stream of new users and content. How can we make recommendations when there isn't enough information about either?

Blog post on 14 Jul 2023

We need to talk about recommendations: helping curators and data scientists work better together

Communication is key to enabling curators and data scientists to work towards the same goals - but often recommendation systems are understood in very different ways.

Blog post on 17 May 2023

AI-assisted journalism: our open-source quote extraction system

We are releasing an open-source quote extraction and attribution system called Citron.

Blog post on 19 Apr 2023

Data Science Research Partnership

The Data Science Research Partnership aims to put the �鶹Լ�� at the forefront of machine learning and data science for the media industry, unlocking the potential of the �鶹Լ��’s data...

Project

Social TV and the future of data

The future of social TV is fun, smart and safe - launching next-generation social TV in collaboration with Tim Berners Lee's team.

Blog post on 26 Oct 2022

White Paper WHP 402: Old School: An 8K Multicamera Shoot to Create a Dataset for Computational Cinematography

Graeme Phillipson, Stephen Jolly, Alia Sheikh, Peter Mills, Rebecca Stagg, Michael Evans

R&D designed an 8K multi-camera production, to create a dataset to help further research into AI automated editing systems

White paper published Aug 2022

A new dataset to improve TV production using artificial intelligence and machine learning

A TV shoot designed to be edited by a machine learning program or artificial intelligence. Our open-source dataset is for AI production and intelligent cinematography researchers.

Blog post on 17 May 2022

Using artificial intelligence to automatically segment media content

Media consumption continues to evolve, with rising interest in short-form content - and segments or clips of �鶹Լ�� programmes are an excellent source.

Blog post on 4 Apr 2022

Releasing the largest British Sign Language dataset for research

A new dataset of British Sign Language footage to help academic researchers interested in automated sign language recognition has just been released.

Blog post on 19 Nov 2021

Sustainable futures: Designing a secure carbon calculator

Investigating the potential of a personal data-driven climate impact calculator that puts users' privacy first.

Blog post on 26 Oct 2021

Personal data stores: building and trialling trusted data services

Sir Tim Berners-Lee, wants to reconfigure the web so users own and control their data. We are investigating how to give young people the chance to do just that.

Blog post on 29 Sep 2021

Ethics of recommendation systems in public service media

We are collaborating with the Ada Lovelace Institute to explore the ethical implications of recommendation systems in public service media.

Blog post on 5 Aug 2021

Creating automatic video summaries with text queries

Can we auto summarise a video to help producers and editors work efficiently?

Blog post on 1 Jul 2021

�鶹Լ��

Accessibility links

Research & Development

Data topic

All activity (27)