Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching

This article examines how students (N=198; aged 13 to 17) experienced the new methods for sensor-based learning in multidisciplinary teaching in lower and upper secondary education that combine the use of new sensor technology and learning from self-produced well-being data. The aim was to explore how students perceived new methods from the point of view of their learning and did the teaching methods provide new information that could promote their own well-being. We also aimed to find out how to collect digital well-being data from a large number of students and how the collected big data set can be utilized to predict school success from the students' well-being data by using machine learning methods (lasso regression and multilayer perceptron). Results showed that sensor-based learning can promote students' learning and well-being. All upper secondary school (n=37) and 87% of lower secondary school pupils (n=161) argued that when data are produced by their bodies, learning is more interesting, and they mostly found that well-being analysis was useful (upper secondary 97%; lower secondary 78%) and can improve personal well-being (upper secondary 78%; lower secondary 67%). The predictive powers with lasso regression and multilayer perceptron (MLP) were quite weak (correlation:-0.14 and 0.34, respectively).