Detecting Flow via a Machine Learning Model in a MOOC Context
Résumé
Flow is a human psychological state positively correlated to self-efficacy, motivation, engagement, and academic achievement, all of which positively affect learning. However, automatic, real-time flow detection is extremely difficult, a challenge particularly exacerbated in a Massively Online Open Course (MOOC) context, where the distant, and asynchronous components rejoin the educational and online context. We approach this issue by training a Machine Learning (ML) model to detect flow transparent and automatically in a MOOC. We pair the results of the EduFlow2 and Flow-Q questionnaires (n = 1 553, two years data collection), and their MOOC log data (French MOOC “Gestion de Projet” [Project Management]) to a ML pipeline to create a ML model that detects flow (ROC = 0.68 and PRC = 0.87) in a MOOC context. This ML model detects flow (0.85) with a greater Precision than its absence (0.34).