Measurement of student engagement in the STEM classroom using machine learning and biometrics

#STEM #Biometrics #Machine #Learning #Assessment

The measurement of student engagement in STEM courses is investigated using machine learning and biometrics to measure the emotional and behavioral states of students in the classroom. The approach collects multi-dimensional biometrics via camera and wristband monitors of facial expressions, eye gaze, hand/head/body movement, and heart rate. From these data, a software model is trained to classify student engagement. Engagement is classified from behavioral and emotional states with cognitive engagement inferred by machine learning. The ability to measure student engagement in real time can be used by the instructor to tailor the presentation of material in class, identify course material that engages and disengages with students, and identify students that are engaged, or disengaged and at risk of failure. Further, this approach allows quantitative comparison of teaching methods, such as lecture, flipped classrooms, classroom response systems, etc. such that an objective metric can be used to close the loop on teaching evaluation.

This work has been funded by the NSF.