Automatic Identification of Questions in MOOC Forums and Association with Self-Regulated Learning - Archive ouverte HAL
Communication Dans Un Congrès Année : 2019

Automatic Identification of Questions in MOOC Forums and Association with Self-Regulated Learning

Résumé

Discussion forums can be a rich source to analyze students' questions but it can be challenging to find relevant categories of questions. We considered here students' posts from the discussion forum of four editions of a same French MOOC on Project Management. We extended a coding scheme to annotate questions based on their content (course vs. non course) and trained 3 stages of an automatic annotation model. Then we studied the correlation between the nature of the questions asked and students' performance and self-regulation. The results are promising and reveal, for the minority of students active on forums, the possibility to use this feature to better estimate their performance and some of their self-regulation skills based on questions they ask.
Fichier principal
Vignette du fichier
EDM_19.pdf (203.12 Ko) Télécharger le fichier
Poster_EDM19_v4.pdf (477.79 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02157335 , version 1 (20-06-2019)

Identifiants

  • HAL Id : hal-02157335 , version 1

Citer

Fatima Harrak, François Bouchet, Vanda Luengo, Rémi Bachelet. Automatic Identification of Questions in MOOC Forums and Association with Self-Regulated Learning. Educational Data Mining, Jul 2019, Montréal, Canada. pp.564-567. ⟨hal-02157335⟩
281 Consultations
232 Téléchargements

Partager

More