320 Int. J. Computer Applications in Technology, Vol. 33, No. 4, 2008 Copyright © 2008 Inderscience Enterprises Ltd. Multiagent system for learning objects retrieval with context attributes Ana-Belén Gil-González* and Francisco García-Peñalvo Sciences Faculty, Department of Computer Science and Automation, University of Salamanca, Plaza de la Merced S/N, 37008, Salamanca, España Fax: +34-923-294514 E-mail: abg@usal.es E-mail: fgarcia@usal.es *Corresponding author Abstract: Educational standards that include content metadata description for materials have great potential for managing e-learning information and content units and facilitate their interoperability and reutilisation. These open semantic and distance learning aspects contribute new and important possibilities for online education systems. The Learning Objects (LOs) paradigm focuses this new gap on the management and exchange of educational materials. This paper presents an application approach to educational content recommendation based on Learning Objects. It describes an architecture based on a multi-agent system with a bio-inspired algorithm rooted in self-organisation theory. It supports the retrieval, search, selection and composition of these LOs. Keywords: multiagent system; LOs; learning objects; information recovery; semantic web; e-learning. Reference to this paper should be made as follows: Gil-González, A-B. and García-Peñalvo, F. (2008) ‘Multiagent system for learning objects recovery with context attributes’, Int. J. Computer Applications in Technology, Vol. 33, No. 4, pp.320–326. Biographical notes: A.B. Gil-González holds a MCS from the University of Salamanca (Spain) where she is currently pursuing her PhD in Computer Science. She is currently an Assistant Professor in the Department of Computer Science, University of Salamanca. Her current research interests include applied semantic web, software agents, human-computer interaction and community-enabling technology. F. García-Peñalvo graduated from the University of Valladolid with a Degree in Computer Science and later received his PhD from the University of Salamanca. He is currently a Senior Lecturer in the Department of Computer Science of the University of Salamanca. He leads the GRoup of InterAction & eLearning (GRIAL), a research group whose main lines of work are Man-machine interaction, web engineering, software engineering, educational computing and communications theory. 1 Introduction The growth of the web has made it the largest repository of information that has ever existed. Its large size, together with the heterogeneity of the information that it contains, poses serious limitations when performing searches and retrieving information of interest. The development of the semantic web is a promising advance in the transition from the current web to the generation of well-described and structured contents. It is evident that organising all the information by specialised domains, establishing ontologies of consensus, is currently a Utopian concept. However, much effort has been made in this sense, with the development of languages, tools, standards and infrastructures that provide the possibility of generating software tools that will permit contents to be drawn up, facilitate effective and automated management of large volumes of information, and so on, with semantic contents. One of the main foci of the direct application of the semantic web is being developed around educational resources on the web, opening up an important possibility for improving online education systems. Of special relevance are works related to the paradigm of so-called Learning Objects (LOs). Educational standards are being worked on which permit the generation and retrieval of all related information, educational modelling languages that describe the resources with metadata in order to facilitate the interoperability and reuse of components for diverse platforms, and that permit contents to be structured in a way so as to attend to their pedagogical meaning in an instructional context.