A survey of biometric and machine learning methods for tracking students' attention and engagement

Abstract

The skills of focusing and paying attention are critical to student learning. According to Piontkowski et al. [40], "Educators often talk about attention as a general mental state in which the mind focuses on some special feature of the environment. As such, attention is considered essential for learning. It is hard to believe that the student who disregards instruction will benefit from it. Thus, the teacher needs reliable signs of the student’s state of attention."It is challenging, however, for instructors to ascertain signs of student attention in large classrooms with many students. Additional challenges arise in online classrooms, which often limit instructors to watching students’ body language in video feeds, where they cannot see, for example, distractions in the students’ environment. Biometrics and machine learning approaches can help instructors evaluate their students’ level of attentiveness in both physical and online classrooms and introduce appropriate interventions to improve learning outcomes. Although the field of automated attention tracking research is steadily amassing new publications, no survey works have charted the progress of research or encouraged new research. We have filled this gap with this survey of salient works that use biometrics and machine learning to track attention. Specifically, we focus on discussions and analyses of methods that use eye gazing, facial movements and expressions, behavioral biometrics such as body movements, analyses of brainwave signals and psychological states, and multimodal biometrics. We conclude with a discussion of promising future research directions with focus on multimodal biometric techniques.