Sleepers' lag - study on motion and attention

Abstract

Body language is an essential source of information in everyday communication. Low signal-to-noise ratio prevents us from using it in the automatic processing of student behaviour, an obstacle that we are slowly overcoming with advanced statistical methods. Instead of profiling individual behaviour of students in the classroom, the idea is to compare students and connect the observed traits to different levels of attention. With the usage of novel techniques from the field of computer vision, we focus on features that can be automatically extracted with a system of cameras, by means of passive observation of the classroom population. We show parallels between our work and previous theories and formulate a new concept for measuring the level of attention based on synchronization of student body movement. We observed that students with lower levels of attention are slower to react than focused students, a phenomenon we named "sleepers' lag." This realization may give rise to novel measurements that can act as a technological support for teacher metacognition. The goal is to improve the teacher-student conversation and to propose techniques that can enable a shorter feedback loop of the teacher's performance compared to the current-day methods.

Multimodal Learning Analytics and Education Data Mining: using computational technologies to measure complex learning tasks

“…Raca, Tormey, and Dillenbourg (2014), for instance, are pioneering ways of capturing student engagement and attention by conducting frame-by-frame analyses of videos taken from the teacher's position. They show that students' motion and level of attention can be estimated using computer vision, and that individuals with lower levels of attention are slower to react than focused students.…”

Classroom Social Signal Analysis

“…Our initial set of experiments on motion showed no direct connection between the motion of the students and their attention levels (reported in the questionnaires), but gave grounds for the definition of the concept of "motion lag" (Raca, Tormey, & Dillenbourg, 2014)  the idea that high-attention students will more likely be synchronized in their actions. From this, we hypothesize that the synchronization influence comes from the external environment, and that the dominant signal in a good classroom will be the teacher.…”

Holistic Analysis of the Classroom

“…With the introduction of reliable pose estimations, explorations spread into body movement, with the cost of introducing a depth-camera capturing constraints [28]. In the learning domain, studies in motion tracking in the classroom [23] [22] indicate that there are multiple measurements which can be potentially useful for teacher's performance and audience behavior analysis. Facial features have been explored before in single-user settings with significant success [14], and more complex multi-modal systems for emotional assessment are also known in the literature [3], …”

“…With the maturing of the techniques and cheaper consumer-level sensors, the benefits of developed audio analysis (speech recognition, speaker differentiation), video processing (face detection, person tracking, pose estimation), written material analysis (OCR, augmented reality) are trickling down from specialized areas into different usage scenarios. In the case of education, these techniques now allows us to capture the aspects of the learning experience such as classroom interaction [23], content generation [20], discussion dynamics [4][26] and others, while still remaining unobtrusive [29].…”