IntelliEye

Abstract

A main weakness of the Massive Open Online Learning movement is retention: a small minority of learners (on average 5-10%, in extreme cases <1%) that start a MOOC complete it successfully. There are many reasons why learners are unsuccessful, among the most important ones is the lack of self-regulation: learners are often not able to self-regulate their learning behavior. Designing tools that provide learners with a greater awareness of their learning is vital to the future success of MOOC environments. Detecting learners' loss of focus during learning is particularly important, as this can allow us to intervene and return the learners' attention to the learning materials. One technological affordance to detect such loss of focus are webcams-ubiquitous pieces of hardware available in almost all laptops today. Recently, researchers have begun to make use of webcams as part of complex machine learning-based solutions to detect inattention or loss of focus based on eye tracking and eye gaze data. However, those approaches tend to have a high detection lag, are inaccurate, and are complex to design and maintain. In contrast, in this paper, we explore the possibility to make use of simple metrics such as gaze presence or face presence to detect a loss of focus in the online learning setting. To this end, we evaluate the performance of three consumer and professional eye-tracking frameworks using a benchmark suite we designed specifically for this purpose: it contains a set of common xMOOC user activities and behaviours. The results of our study show that already those simple metrics pose a significant challenge to current hard-and software-based eye-tracking solutions.

Self-Regulated Learning in Massive Online Open Courses: A State-of-the-Art Review

“…Robal et al [34] meanwhile, argue that many of the MOOCs currently available focus on video conferencing. In this sense, they designed a privacy system called IntelliEye, which makes use of the students' web cameras to determine, in real time, the moments the students are not paying attention during these video-conferences, notifying them of the situation.…”

Using Learner Reviews to Inform Instructional Video Design in MOOCs

“…Aggregation of these findings highlights the importance of designing shorter videos for MOOCs, as videos are the primary source of instructional content in MOOCs. This is because there are many distractions present around the learners, which can result in them losing focus, particularly those learners who lack self-regulation skills [ 72 , 73 ]. Future research could explore educational interventions to foster video engagement and reduce attention loss beyond designing shorter MOOC videos.…”

Could the Use of AI in Higher Education Hinder Students With Disabilities? A Scoping Review

“…Less frequently, authors explained the importance of guaranteeing privacy in the design of their applications. For instance, Robal et al [36] argued that their system for detecting attention loss in online learning was privacy-aware, as data were stored on local machines. Alike, Jia et al [37] specifically investigated for the problem that algorithms may generate private content.…”

“…Assessment and evaluation applications assessed 1) students' knowledge and skills [73]- [82], 2) their attention [36], [83]- [85], and 3) academic integrity and attendance [48], [86]- [88]. All solutions aimed to support instructors' grading and can impact student performance and chances of graduation.…”

“…For instance, Rodriguez-Ruiz et al [80] assessed communication skills of software engineers by categorizing students according to their personality traits: verbally expressive, passionate, and perceptive. Similarly, systems assessing students' attention usually indicated to lecturers what a student was doing (e.g., listening, looking at phone, taking notes, chatting) [36], [83], [84], or gave an attention score [85]. Alike, the solutions provided instructors with binary output that checked academic integrity [48], [86], [87] or class attendance [88].…”