Analysis of students clustering results based on Moodle log data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Analysis of students clustering results based on Moodle log data

Résumé

This paper describes a proposal of relevant clustering features and the results of experiments using them in the context of determining students' learning behaviors by mining Moodle log data. Our clustering experiments tried to show whether there is an overall ideal number of clusters and whether the clusters show mostly qualitative or quantitative differences. They were carried out using real data obtained from various courses dispensed by a partner institute using a Moodle platform. We have compared several classic clustering algorithms on several group of students using our defined features and analysed the meaning of the clusters they produced.
Fichier principal
Vignette du fichier
bovo_13222.pdf (118.75 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01146267 , version 1 (28-04-2015)

Identifiants

  • HAL Id : hal-01146267 , version 1
  • OATAO : 13222

Citer

Angela Bovo, Stephane Sanchez, Olivier Héguy, Yves Duthen. Analysis of students clustering results based on Moodle log data. 6th International Conference on Educational Data Mining - EDM 2013, Jul 2013, Memphis, Tennessee, United States. pp. 306-307. ⟨hal-01146267⟩
239 Consultations
320 Téléchargements

Partager

Gmail Facebook X LinkedIn More