Title: Relevant learning objects extraction based on semantic annotation

Authors: Boutheina Smine; Rim Faiz; Jean-Pierre Desclés

Addresses: Languages, Logic, Informatics and Cognition (LaLIC), University of Paris Sorbonne, 28 Rue Serpente, 75006 Paris, France ' LARODEC, IHEC-University of Carthage, 2016 Carthage Présidence, Tunisia ' Languages, Logic, Informatics and Cognition (LaLIC), University of Paris Sorbonne, 28 Rue Serpente, 75006 Paris, France

Abstract: We propose, in this paper, a model that extracts automatically learning objects as response to a user request. To do this, we proceed by automatically annotating texts with semantic metadata. These metadata will allow us to index and extract learning objects from texts. Thus, our model is composed of two principal parts: the first part consists of a semantic annotation of learning objects according to their semantic categories (definition, example, exercise, etc.). The second part uses automatic semantic annotation which is generated by the first part to create a semantic inverted index able to find relevant learning objects for queries associated with semantic categories. We add a secondary part to our model which sorts the results offered to the user according to their relevance. We have implemented a system called SRIDoP, on the basis of the proposed model and we have verified its effectiveness.

Keywords: semantic annotation; learning objects; document indexing; pedagogical documents; contextual exploration; object extraction; text annotation; semantic metadata.

DOI: 10.1504/IJMSO.2013.054187

International Journal of Metadata, Semantics and Ontologies, 2013 Vol.8 No.1, pp.13 - 27

Received: 18 Jun 2012
Accepted: 21 Feb 2013

Published online: 28 May 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article