Une architecture multi-agents pour des sessions d'apprentissage collaboratif

Abstract : Collaboration between learners can have a positive impact in a learning session only if learners can exchange efficiently. discussions, advices given by a colearner are good means to help a learner in knowledge understanding. One of the main problems in a collaborative learning activity is to create coherent groups among students. In this paper, we present an architecture that aims to address this question. We use a neural network algorithm to obtain homogenous groups. An architecture based on several agents is then able to select the more relevant group and provide the learning session with information related to the subject.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://edutice.archives-ouvertes.fr/edutice-00000673
Contributor : Corinne Gervais <>
Submitted on : Thursday, November 4, 2004 - 4:34:27 PM
Last modification on : Tuesday, September 17, 2019 - 9:36:46 AM
Long-term archiving on : Thursday, April 1, 2010 - 3:37:17 PM

Identifiers

  • HAL Id : edutice-00000673, version 1

Collections

Citation

Emmanuel Blanchard, Claude Frasson. Une architecture multi-agents pour des sessions d'apprentissage collaboratif. Technologies de l'Information et de la Communication dans les Enseignements d'ingénieurs et dans l'industrie, Nov 2002, Villeurbanne, France. pp.283-287. ⟨edutice-00000673⟩

Share

Metrics

Record views

229

Files downloads

146