Student Capstone: Is football commentary racially biased?
A player's power gets praised very differently depending on the colour of their skin, and LIS BASc (Bachelor of Arts and Science) graduate Alex Doyle set out to prove it.
For his Capstone Project, he analysed commentary from over 1,100 match highlights and 800 Premier League players, using AI to build composite "average faces" for words like 'intelligent' and 'powerful'.
The results were stark: cognitive praise skewed lighter-skinned, physical praise skewed darker-skinned. Watch our video essay to find out how he did it.
Alex's project is a good example of what the BASc lets students do with a passion that doesn't fit neatly into one subject. He didn't have to choose between studying football and studying racial bias, or between the technical work of building AI models and the critical thinking needed to interpret what they show. The degree's structure, built around interdisciplinary methods rather than a single discipline, meant he could bring computer science, data analysis, and social science together to interrogate something he actually cared about. That's the pitch behind the BASc more broadly: whatever you're passionate about, whether it's sport, cities, science, or humanities, there's likely a way to study it that doesn't force you to leave half your interests at the door.
Citations:
’Racial Bias in Football Commentary’ by Danny McLoughlin, (2021).
Dataset from 1,100 match highlights from GOAL dataset by Allessandro Suglia et al (2022).
Share this story
.jpg)
Sign up for our newsletter
Don't miss out on important updates including course information, new announcements, Open Day dates and the latest LIS news.
.svg)
This is a comment related to the post above. It was submitted in a form, formatted by Make, and then approved by an admin. After getting approved, it was sent to Webflow and stored in a rich text field.