Learning Pulse

Learning Pulse explored whether using a machine learning approach on multimodal data such as heart rate, step count, weather condition and learning activity can be used to predict learning performance in self-regulated learning settings. The experiment lasted eight weeks involving nine PhD students as participants wearing a Fitbit HR wristband and having the applications on their computer recorded during their learning activities. A software infrastructure for collecting multimodal learning experiences from different sources was implemented based on the xAPI standard and stored in a cloud-based Learning Record Store. As part of this infrastructure, a Data Processing Application was developed to pre-process, analyse and generate predictions to provide feedback to the users about their learning performance. The participants of the experiment were asked to rate their learning experience through an Activity Rating Tool indicating their perceived level of productivity, stress, challenge and abilities. These self-reported performance indicators were used as markers to train a Linear Mixed Effect Model to generate learner-specific predictions of the learning performance.

  • Purpose: Master thesis project
  • Keywords: Learning Analytics, Fitbit, Biofeedback
  • Where: Open University of The Netherlands - Maastricht University, The Netherlands
  • Supervised by: Hendrik Drachsler (OUNL); Stefaan Ternier (OUNL); Pietro Bonizzi (UM); Kurt Driessens
  • When: September 2015 - June 2016