The British Board of Film Classification (BBFC) has announced the first phase of its development project to explore the use of AI systems in content classification. Driven by the BBFC’s huge dataset and human insight from over a century of viewing content, and taking advantage of AWS cloud services that support AI tools, the project will complement the BBFC’s existing classification and compliance processes.
Their AI systems will build on the BBFC’s long-standing classification expertise, and are designed to make the human viewing process more efficient. With the recent recruitment of four new Compliance Officers, this larger team will continue to be at the centre of classification for years to come. Their expertise will always remain essential in ensuring the BBFC’s classification practices remain in step with the expectations of UK audiences.
Developing a Prototype
Partly funded by Innovate UK, the BBFC is developing a prototype for a bespoke AI tool that will identify and tag content issues, and is working in collaboration with the AWS Machine Learning Solutions Lab and AWS Professional Services teams. AWS have supplied their machine learning (ML) and natural language processing (NLP) systems to develop this tool in ways that will make use of multiple techniques.
The alpha testing phase is currently underway and demonstrates promising initial figures. So far, the tool achieves 80% accuracy when identifying content issues. Initial statistics also highlight the potential for this tool to help compliance teams increase their efficiency significantly by delivering potential time-savings of 60%. The project is further supported by the Department of Computer Science at the University of Bath to maintain high levels of data ethics and to mitigate data and algorithmic bias.
International Age Ratings
Further to this, the BBFC is building a separate tool to determine and assign international age ratings, which can be used in conjunction with the tagging tool. This scalable feature aims to enable distributors and streaming services to obtain age ratings and content advice for multiple territories in a streamlined and cost-effective way. Both of these tools share the ultimate goal of driving down the cost of classification in the future.
With the BBFC’s expertly-trained Compliance Officers as the drivers of these AI tools now and into the future, the project will help the BBFC explore innovative classification methods to meet the changing ways in which people watch and consume content.
The BBFC’s classification standards are supported by published Classification Guidelines, which set the foundation for all classification decisions and are informed through research with more than 10,000 people across the UK to ensure classification decisions reflect current UK societal standards. The guidelines are updated every 4 to 5 years and the BBFC is consulting on its guidelines this year, with any changes required by the research coming into effect in early 2024.
Tools in Development
The Tagging tool is software produced in collaboration with Amazon Web Services (AWS) that aims to identify and tag content issues in line with the BBFC's published Classification Guidelines, which are reviewed by BBFC Compliance Officers and used to generate BBFC age ratings.
The new Age Rating tool, designed to be used in conjunction with the Tagging tool, is a patented scalable software that uses AI to learn the correlation between classification issues in accordance with the BBFC's Classification Guidelines, as well as classification issues in other territories. Over time, the AI collects a list of rules which it uses to generate accurate, localised age ratings for territories across the globe. These rules will be continually updated as new content and classification standards become available.
“What is particularly timely about this project is the opportunity it provides to put into practice the principles set out in the emerging standards at ISO and IEEE,” said Julian Padget, Department of Computer Science at the University of Bath. “The formation of the BBFC’s AI Ethics Committee is a clear step in the BBFC’s ongoing commitment to establish policies and procedures concerning AI ethics, and we are pleased to contribute to those activities. We look forward to continuing to share our expertise to ensure that the project’s processes and outputs are benefiting from the latest thinking on the consideration of bias in data-driven systems.”
Esra Kasapoglu, Director of AI and Data Economy at Innovate UK said, “The British Board of Film Classification (BBFC) plays a significant role in helping UK audiences choose the content that’s right for them and ensuring classification decisions reflect UK societal standards. The announcement of this project is a major milestone that we are delighted to see achieved through industry collaboration. Pioneered by the BBFC, this innovative technology will be complementary to the human expertise honed by viewing content for more than a century. As part of UK Research and Innovation, Innovate UK supports this new project at a pivotal time for the industry, and believes it will assist other creatives and innovators across the country.” aws.amazon.com