Towards a Machine Learning flow-predicting model in a MOOC context - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Towards a Machine Learning flow-predicting model in a MOOC context

Sergio Ramirez
Nour El Mawas
Rémi Bachelet
Jean Heutte

Abstract

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 prediction is quite difficult, particularly in a Massively Online Open Course context, even more so because of its online, distant, asynchronous, and educational components. In such context, flow prediction allows for personalization of activities, content, and learning-paths. By pairing the results of the EduFlow2 and Flow-Q questionnaires (n = 1589, two years data collection) from the French MOOC “Gestion de Projet” (Project Management) to Machine Learning techniques (Logistic Regression), we create a Machine Learning model that successfully predicts flow (combined Accuracy & Precision ~ 0.8, AUC = 0.85) in an automatic, asynchronous fashion, in a MOOC context. The resulting Machine Learning model predicts the presence of flow (0.82) with a greater Precision than it predicts its absence (0.74).
No file

Dates and versions

halshs-03606527 , version 1 (11-03-2022)

Identifiers

  • HAL Id : halshs-03606527 , version 1

Cite

Sergio Ramirez, Nour El Mawas, Rémi Bachelet, Jean Heutte. Towards a Machine Learning flow-predicting model in a MOOC context. 14th International Conference on Computer Supported Education (CSEDU 2022), Apr 2022, Online Streaming, United Kingdom. ⟨halshs-03606527⟩
159 View
0 Download

Share

Gmail Facebook X LinkedIn More