The UK's pioneering Nerve Lab at University of the Arts London is harnessing artificial intelligence to study how children's screen time affects their attention, comprehension, and emotional responses. The lab, which opened earlier this week, is the first facility of its kind in the country, combining wearable brain imaging, motion capture, and AI-powered analytics to monitor real-time reactions to media and artistic experiences.
Understanding Children's Content
Parents are constantly advised to limit children's screen time, but guidance on which films or TV shows are best for developing minds remains largely one-size-fits-all. A slow-paced programme like Bluey offers a different viewing experience compared to a fast-moving action series like PAW Patrol, yet both are considered suitable for young children. This challenge is growing as content evolves.
“Today’s young viewers are increasingly engaging with short-form, fast-paced, highly captivating content, often created by splicing and rearranging existing episodic content into quickly digestible snippets or compilations,” said Prof Tim Smith, director of the Nerve Lab. “This evolution is not only changing how content is produced and distributed, but may also affect children’s attention, comprehension and emotional response.”
The Animating Minds Project
Young children process information differently from adults, yet there is still little evidence about how specific features of children's programmes influence their attention and behaviour. “We have kids as young as two spending three or four hours a day on screens. It is really important to have a wider understanding of what it means for them to watch something that’s appropriate for their age,” said Alisa Musatova, a research assistant on the Animating Minds project.
To understand how different styles of content affect young viewers, Musatova and colleagues have assembled a database of about 1,000 episodes of popular animated TV shows. They use AI-based tools to analyse features such as pacing, colourfulness, loudness, shot frequency, and narrative structure, while interviewing animators and producers about creative decisions. The team is recruiting UK families with children aged three to six for an online study exploring how animated programmes influence short-term attention.
Developing Better Classification Systems
The ultimate goal is to develop tools that help animators, commissioners, and regulators understand whether programmes have the intended effect on their target audience, laying the foundations for more nuanced classification systems. “The question is, can we build a computational system where we can understand and predict the direct effect that children’s animated content is going to have on young children?” said Smith.
Prof Heather Kirkorian, a developmental psychologist at the University of Wisconsin-Madison, agreed that further research is needed. “The digital media landscape has changed a lot in recent years. While there is a lot of speculation about potential impacts on development, there is very little research that uses the types of precise measurement proposed in this work.” She added that AI-based tools could analyse children's programming at a scale previously impractical.
Polly Conway, senior editor at Common Sense Media, said additional evidence about the impact of children's programming on young brains could be valuable. “Just because a programme or YouTube channel is teaching the ABCs, numbers or shapes, they may not be doing it at the correct level for the intended audience.”
Mathstronauts: Personalised Learning with Brain Imaging
Another Nerve Lab project, Mathstronauts, uses brain imaging and behavioural data to investigate individual differences in children's comprehension of maths. For example, two children might answer a fraction question incorrectly for different reasons: one may not understand fractions, while another may struggle to suppress an intuitive response based on whole numbers.
“With conventional testing, I can see whether an answer is correct and how many seconds a child took to solve it, but it doesn’t tell me why two children have made the same mistake,” said Dr Rakhi Leela Nair, leading the project. The hope is that functional near-infrared spectroscopy (fNIRS), a non-invasive brain scanning method, can help unpick what’s going on. Children wear a neoprene cap with sensors that monitor brain activity as they play a maths game. This information, combined with game scores, is used in real time to adapt the game and provide personalised support.
Children who understand the concept but respond impulsively are directed to tasks that encourage slower, more careful thinking. Those who have not mastered the concept receive additional teaching and practice. The system is being tested with seven- and eight-year-olds in a north London primary school.
Prof Roi Cohen Kadosh, a cognitive neuroscientist at the University of Surrey, described the approach as “a plausible and potentially useful direction for educational neuroscience” but cautioned that its value depends on whether brain-imaging data provides insights beyond those from teachers and conventional assessments. He added that technologies like fNIRS should support, not replace, teachers.
