Massive Open Online Courses (MOOCs) have become an attractive opportunity for people around the world to gain knowledge and skills. Despite the initial enthusiasm of the first wave of MOOCs and the subsequent research efforts, MOOCs today suffer from retention issues: many MOOC learners start but do not finish. A main culprit is the lack of oversight and directions: learners need to be skilled in self-regulated learning to monitor themselves and their progress, keep their focus and plan their learning. Many learners lack such skills and as a consequence do not succeed in their chosen MOOC. Many of today's MOOCs are centered around video lectures, which provide ample opportunities for learners to become distracted and lose their attention without realizing it. If we were able to detect learners' loss of attention in real-time, we would be able to intervene and ideally return learners' attention to the video. This is the scenario we investigate: we designed a privacy-aware system (IntelliEye) that makes use of learners' Webcam feeds to determine---in real-time---when they no longer pay attention to the lecture videos. IntelliEye makes learners aware of their attention loss via visual and auditory cues. We deployed IntelliEye in a MOOC across a period of 74 days and explore to what extent MOOC learners accept it as part of their learning and to what extent it influences learners' behaviour. IntelliEye is open-sourced at https://github.com/Yue-ZHAO/IntelliEye.@en

The use of mobile technology has become a part of our daily lives and enabled us to perform tasks that once were possible only on stationary computers on-the-go anywhere and at any time. This shift has also affected the way we learn. The use of mobile devices on-the-go requires users to multitask and divide attention between several activi- ties. In the context of learning, it may lead to high cognitive load and potential disruptions. While many MOOC platforms have provided the possibility for learning on mobile devices, the learning situation and its effect on learners’ while using mobile devices on-the-go has not been stud- ied in full. Contrary to the majority of available mobile learning studies which are conducted in lab conditions, we focus on real-life situations commonly experienced by learners while learning on-the-go. We study the differences in MOOC learners’ performance and interactions in two different learning situations with mobile devices: stationary learning and learning on-the-go on the edX platform.@en

A main weakness of the open online learning movement is retention: a small minority of learners (on average 5-10%, in extreme cases <1%) that start a so-called Massive Open Online Course (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. In recent years, researchers have begun to exploit eye tracking and gaze data generated from webcams as part of complex machine learning solutions to detect inattention or loss of focus. Those approaches however tend to have a high detection lag, can be inaccurate, and are complex to design and maintain. In contrast, in this paper, we explore the possibility of a simple alternative---the presence or absence of a face---to detect a loss of focus in the online learning setting. To this end, we evaluate the performance of three consumer and professional eye/face-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 even this basic approach poses a significant challenge to current hardware and software-based tracking solutions.@en