Romolo Tavani - stock.adobe.com

BBFC taps into AWS AI portfolio to speed up content classification

The British Board of Film Classification has embarked on an exploratory piece of work to see how artificial intelligence could assist with classifying content

The British Board of Film Classification (BBFC) is working with Amazon Web Services (AWS) to explore how artificial intelligence (AI) technologies could be deployed to aid its content classification work.

The alpha phase of the exploratory project is already underway, with the BBFC drawing on its own datasets and the viewing experiences of its staff to train the AI so that content can be classified for compliance purposes.

The BBFC’s classification guidelines are informed by the feedback of more than 10,000 people across the UK to ensure they align with current UK societal standards. They are subject to review and updates every four to five years.

“The BBFC is developing a prototype for a bespoke AI tool that will identify and tag content issues,” the organisation said in a statement. “AWS has provided machine learning and natural language processing technologies to develop this multimodal tool.”

The project is being partially funded by innovation agency Innovate UK, and supported by members of the AWS Machine Learning Solutions Lab and its professional services team, as well as the University of Bath’s Department of Computer Science.

The latter organisation’s involvement in the project is geared towards protecting against algorithmic bias occurring when using the tool.

According to the BBFC, the tool is already capable of identifying content issues with 80% accuracy, prompting the organisation to talk up the technology’s potential to bring large-scale efficiencies to its compliance teams.

Furthermore, the BBFC is also building a separate tool to determine and assign international age ratings for use alongside the tagging tool. It is hoped this will accelerate the time it takes for distributors and streaming services to age rate content in multiple territories.

BBFC president Natasha Kaplinksy said the project was an acknowledgement of the role AI is likely to play in classifying content in the years to come.

“This announcement marks an incredibly exciting transition for the BBFC, as we continue to embrace new technology to help us achieve our core mission of supporting people and families across the UK to make informed viewing decisions about the content they consume,” she said.

“We are exploring ways in which AI might support and enhance the BBFC’s classification work”
Natasha Kaplinksy, BBFC

“We recognise that in the coming years, AI is likely to play a part in a blended approach to classification. Through this project, we are exploring ways in which AI might support and enhance the BBFC’s classification work, including online. I’m proud to be leading such a cultural institution of over 110 years into the future of classification.”

Meanwhile, BBFC CEO David Austin said the project would also go some way to streamlining the processes involved with classifying content, the volume of which has grown massively in recent years, and will benefit the organisation’s compliance officers.

“These products will continue to enable audiences to choose well by increasing coverage of trusted age ratings and content advice that reflect local standards to ensure safer viewing experiences for parents and families. Our industry-leading compliance officers – who are the well-established experts when it comes to content and classification, both offline and online – will be at the very heart of this new classification technology now and in years to come.”

Chris Hayman, director of UK public sector at AWS, said the project would also bring about cost savings for the BBFC.

“The BBFC’s work helps people to make responsible and informed decisions about what they watch, and we’re proud of the work we are doing with the BBFC to explore how the AWS cloud and AI technologies can be used to help classify high volumes of content in a scalable way,” he added.

Read more about cloud and AI

Read more on Software-as-a-Service (SaaS)