Towards a multi-dimensional biometric approach to quantifying student engagement in the STEM classroom

Abstract

This paper is a work in progress, supported by NSF funds, applied to first-year engineering mathematics courses. An approach to performing a quantitative, objective, and real-time measurement of student engagement in the STEM classroom is proposed to initiate a discussion of the concept and use expert opinions of other faculty to guide progress of the work. This will be realized by an engagement measurement system (EMS). The approach observes biometric data from the students and is multi-dimensional in that it incorporates facial expressions, eye gaze, and hand/head/body movement captured by camera, in addition to pulse captured by a wristband device. From these data, a machine-learning model is trained to classify student engagement. Engagement is classified from behavioral, emotional, and cognitive aspects. The ability to measure student engagement 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.