Content uploaded by Ricardo Azambuja Silveira
Author content
All content in this area was uploaded by Ricardo Azambuja Silveira on Apr 20, 2016
Content may be subject to copyright.
Intelligent Learning Objects:
An agent Based Approach of Learning Objects1
Ricardo Azambuja Silveira1, Eduardo Rodrugues Gomes2, Vinicius Heidrich Pin-
to1, Rosa Maria Vicari2
1 Universidade Federal de Pelotas - UFPEL, Campus Universitário, s/nº - Caixa Postal 354
{rsilv, vheidrich}@ufpel.edu.br
2 Universidade Federal do Rio Grande do Sul – UFRGS
Av. Bento Gonçalves, 9500 - Campus do Vale - Bloco IV Porto Alegre - RS -Brasil
{ergomes,rosa}@inf.ufrgs.br
Abstract. Many researchers on Intelligent Learning Environments have pro-
posed the use of Artificial Intelligence through architectures based on agents’
societies. Teaching systems based on Multi-Agent architectures make possible
to support the development of more interactive and adaptable systems. At the
same time many people have been working to produce metadata specification
towards a construction of Learning Objects in order to improve efficiency effi-
cacy and reusability of learning content based on Object Oriented design para-
digm. This paper proposes an agent based approach to produce more intelligent
learning objects according to FIPA agent architecture reference model and
LOM/IEEE 1484 learning object specification learning objects
1 Introduction
Many people have been working hard to produce metadata specification towards a
construction of Learning Objects in order to improve efficiency, efficacy and reusa-
bility of learning content based on Object Oriented design paradigm. According to
Sosteric and Hesemeier [7], learning objects have been on the educational agenda
now. Organizations such as the IMS Global Learning Consortium [4] and the IEEE
[3] have contributed significantly by helping to define indexing (metadata) standards
for object search and retrieval. There has also been some commercial and educational
work accomplished.
Learning resources are objects in an object-oriented model. They have methods
and properties. Typically methods include rendering and assessment methods. Typical
properties include content and relationships to other resources [5]. Downes [2] points
out that a lot of work has to be done to use a learning object. You must first build an
educational environment in which they can function, you need, somehow, to locate
these objects, arrange them in their proper order, according to their design and func-
tion. And you must arrange for the installation and configuration of appropriate view-
1 Published by Springer . DOI: 10.1007/978-3-540-30139-4_108
ing software. Although it seems to be easier to do all this with learning objects, we
need smarter learning objects.
• +
2 – Pedagogical agents: the Intelligent Learning Objects
The idea of Pedagogical Agents in the context of this project was conceptualized in
the same spirit as the learning objects in the sense of efficiency, efficacy and reusabil-
ity of learning content. In addiction, the Intelligent Learning Objects (or Pedagogi-
cal Agents) improve adaptability and interactivity of complex learning environments
built with this kind of components by the interaction among the learning objects and
between learning objects and other agents in a more robust conception of communica-
tion than a single method invocation as the object oriented paradigm use to be. Intel-
ligent Learning Objects (ILO) must be designed according to the Wooldridge, Jen-
nings and Kinny conceptions of agents [8] considering an agent as coarse-grained
computational systems, each making use of significant computational resources that
maximizes some global quality measure, but which may be sub-optimal from the
point of view of the system components.
Fig. 1. The Intelligent Learning Object designed as a Pedagogical FIPA agent implements the
same API specification, performs messages sending and receiving, and performs agents’ specif-
ic task, according to its knowledge base. As the agent receives a new FIPA-ACL message it
processes the API function according to its content, performing the adequate behavior and act
on SCO. According to the agent behavior model, the message-receiving event can trigger some
message sending, mental model updating and some particular specific agent action on the SCO
ILOs must be heterogeneous, in that different agents may be implemented using
different programming languages and techniques and make no assumptions about the
delivery platform The ILOs are created according to the course design in order to
perform specific tasks to create some significant learning experience by interacting
with the student. But the object must do it in a smaller sense as possible in order to
promote reusability and efficiency, and permit a large amount of different combina-
tion with other objects. In addition, an most important, the ILOs must be designed by
the course specialist The smaller and most simple is the pedagogical task performed
by the ILO, the most adaptable flexible and interactive is the learning experience
provided by it.The FIPA-ACL protocol performed by a FIPA agent communication
manager platform ensures an excellent support for cooperation. Fig 1 shows the pro-
posed architecture of the set of pedagogical agents.
The Sharable Content Object Reference Model (SCORM®) [1] is maybe the best
reference to start a thinking of how to build learning objects based on a agent archi-
tecture. The SCORM defines a Web-based learning “Content Aggregation Model”
and “Run-time Environment” for learning objects. At its simplest, it is a model that
references a set of interrelated technical specifications and guidelines designed to
meet the requirements for object learning. Learning content in its most basic form is
composed of Assets that are electronic representations of media, text, images, sound,
web pages, assessment objects or other pieces of data that can be delivered to a Web
client.
3 Conclusions
At this point, we quote Downes [2]: We need to stop thinking of learning objects as
chunks of instructional content and to start thinking of them as small, self-reliant
computer programs. When we think of a learning object we need to think of it as a
small computer program that is aware of and can interact with its environment.
This project is granted by Brazilian research agencies: CNPq and FAPERGS.
5 Bibliography
1. Advanced Distributed Learning (ADL)a. Sharable Content Object Reference
Model (SCORM ® ) 2004 Overview. 2004. Available by HTTP in:
<www.adlnet.org>.
2. DOWNES , Stephen Smart Learning Objects, May 2002
3. IEEE Learning Technology Standards Committee (1998) Learning Object Metadata
(LOM): Draft Document v2.1
4. IMS Global Learning Consortium. IMS Learning Resource Meta-data Best Practices
and Implementation Guide v1.1. 2000.
5. ROBSON, Robby (1999) Object-oriented Instructional Design and Web-based
Authoring. [Online] Available by HTTP in:
<www.eduworks.com/robby/papers/objectoriented.pdf>
6. SHOHAM, Y Agent-oriented programming. Artificial Intelligence, Amsterdam,
n.60, v.1, p.51 - 92, Feb. 1993.
7. SOSTERIC, Mike, HESEMEIER Susan When is a Learning Object not an Object: A
first step towards .a theory of learning objects International Review of Research in
Open and Distance Learning (October - 2002) ISSN: 1492-3831
8. WOOLDRIDGE, M.; JENNINGS, N. R.; KINNY, D. A methodology for agent-
oriented analysis and design. In: INTERNATIONAL CONFERENCE ON
AUTONOMOUS AGENTS, 3. 1999. Proceedings…
