Supporting Self-Regulation Learning Using a Bayesian Approach. Some Preliminary Insights - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Supporting Self-Regulation Learning Using a Bayesian Approach. Some Preliminary Insights

Abstract

Self-Regulated Learning (SRL) is actually challenging modern online environments (e-learning platforms, MOOCs, exercise-based platforms, ...). A large emergent literature points out the need for empirical studies on approaches that can help to build tools for measuring and scaffolding SRL. This paper is a state of the art aiming to identify a set of key avenues to conduct a future experimental research on this theme. More importantly, we present the approaches of Open Learner Models, and knowledge Tracing through Bayesian Networks that offer promising insights to model student knowledge, measure SRL levels and provide appropriate interventions to foster student SRL skills.
Fichier principal
Vignette du fichier
AI4EDU__IJCAI_2021.pdf (106.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03325733 , version 1 (26-08-2021)

Identifiers

  • HAL Id : hal-03325733 , version 1

Cite

Fahima Djelil, Jean-Marie Gilliot, Serge Garlatti, Philippe Leray. Supporting Self-Regulation Learning Using a Bayesian Approach. Some Preliminary Insights. International Joint Conference on Artificial Intelligence IJCAI-21, Workshop Artificial Intelligence for Education, Aug 2021, Montreal (virtual), Canada. ⟨hal-03325733⟩
119 View
75 Download

Share

Gmail Facebook Twitter LinkedIn More