Scalable Mind-Wandering Detection for MOOCs

A Webcam-Based Approach

Conference paper (2017)

Authors

Y. Zhao Web Information Systems - EEMCS
C. Lofi Web Information Systems - EEMCS
C. Hauff Web Information Systems - EEMCS
Research Group
Web Information Systems (EEMCS) (TU Delft)
Mind-wandering MOOCs Learning analytics Eye tracking
More Info
expand_more

Published Date

2017

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Software Technology

Research Group

Web Information Systems

Abstract

Mind-wandering or loss of focus is a frequently occurring experience for many learners and negatively impacts learning outcomes. While in a classroom setting, a skilled teacher may be able to react to students’ loss of focus, in Massive Open Online Courses (MOOCs) no such intervention is possible (yet). Previous studies suggest a strong relationship between learners’ mind-wandering and their gaze, making it possible to detect mind-wandering in real-time using eye-tracking devices. Existing research in this area though has made use of specialized (and expensive) hardware, and thus cannot be employed in MOOC scenarios due to the inability to scale beyond lab settings. In order to make a step towards scalable mind-wandering detection among online learners, we propose the use of ubiquitously available consumer grade webcams. In a controlled study, we compare the accuracy of mind-wandering detection from gaze data recorded through a standard webcam and recorded through a specialized and high-quality eye tracker. Our results suggest that a large-scale application of webcam-based mind-wandering detection in MOOCs is indeed possible.