Detecting distracted students in educational VR environments using machine learning on eye gaze data

Higher Education in the Pacific Alliance: Descriptive and Exploratory Analysis of the Didactic Potential of Virtual Reality

“…Among them, the costs that teachers attribute to the implementation of VR technologies that hinder their integration in higher education stand out [18]. In addition, the use of interactive virtual environments generates a source of visual and auditory stimuli that can have a distracting effect on the student and distract them from the learning objectives, which is why devices have been designed to monitor the use of VR to control student distractions [39].…”

Tutor In-sight: Guiding and Visualizing Students’ Attention with Mixed Reality Avatar Presentation Tools

“…Our proposed teacher dashboard visualises eye-gaze data as a proxy for students' attention since previous studies used eye-gaze to identify mind wandering [11], distraction [6], and interaction strategies [46]. However, since the dashboard presents the information in real-time, we have chosen to show the eye location data as they are.…”

“…As suggested by the participants, another important feature is the post-class statistics, which should be visualised using a separate post-class dashboard as described in Mazza and Dimitrova [42] or Xhakaj et al [74]. This dashboard could potentially integrate advanced techniques [6,11] to analyse eye-gaze sequence to quantify student's attention and detect mind wandering or distraction. This post-class dashboard design and development, however, is beyond the scope of this research and will be left for future development.…”

“…Consequently, an alternative monitoring tool that strikes a balance between monitoring critical data and protecting privacy is necessary. The "black box" characteristic of machine learning monitoring tools (as shown by Asish et al [6]) has the potential to meet this requirement, but further investigation is necessary for its practical usage.…”