From left: Lisa Sanders (Psychological & Brain Sciences), VP Nguyen (CICS), Yimeng Wang (Psychological & Brain Sciences), Sidharth Anupkrishnan (CICS)
Universities are putting significant effort into helping students from a wider range of backgrounds feel that they belong and can succeed in a teaching environment.
But how do we know which particular teaching practices are actually working? Course evaluations and student surveys offer some insight, but they usually come after the fact and can miss what happens moment to moment in the classroom.
This project takes a different approach: measuring student engagement, as it happens, through physiological signals. Bringing together researchers in psychology, neuroscience, and computer science, the team will test whether wearable tools—tracking signals like brain activity, eye movement, and skin conductance—can capture how students are responding during live lectures.
They also hope to correct a longstanding bias in physiological research itself. Many traditional brain-measurement tools work poorly for certain hair textures and styles, limiting who can participate. By testing more flexible devices, the team aims to develop methods that are both scientifically reliable and more inclusive.
To begin, the team will collect data from students listening to live lectures in a laboratory setting designed to resemble a classroom. The team will then use machine learning to identify which signals best predict engagement and learning, with the long-term goal of bringing these insights into real classroom settings.
Over time, this work could lead to new ways of understanding how students experience teaching as it unfolds, help educators refine their practices, and expand who is represented in the research that shapes education.