Lorenzo Moreno, Carina S. González, Evelio J. González
Beatrice Popescu and Claudia L. Oliveira
Departamento de Ingeniería de Sistemas y Automática y ATC, University of La Laguna
La Laguna, CP 38207, Tenerife, Spain
Keywords: Conceptual graphs, Student model, Progressive inquiry, Bayesian networks.
Abstract: This paper present a tool called SIENA that helps in the building knowledge in an autonomous learning
process through: a) an open student model; and b) a student conceptual map to explorer and for
instrospection. However, this new tool uses adaptive tests based on a Progressive Inquiry (PI) model. This
tool has been used for teaching Computer Architecture in the School of Computer Science in the University
of La Laguna, Canary Island.
The european convergence process proposes an
European Space of High Education which has
involved to remove a teaching-learning centered in
the teacher and a passive traditional learning and it
proposes a new model which is centered in the
learner and the second part of the binomial teaching-
learning. Moreover, the concept of e-learning is
moving to e-learning 2.0, where the keys and tools
are the social nets, the collaboration and the
autonomy, where the student can control his own
learning (Kay, 2001).
New technologies have contributed to this new
approach with blending learning and social tools. In
order to obtain this kind of learning and the same
time a significative learning where it is emphasized
the social component of learning is essential to
create new tools, new learning materials as well as
specific applications in different subjects of
On the other hand, the key in the educational
process is that students can achieve the learning
objectives effectively. That means to help the
student acquire the required level of knowledge and
skills in the subject domain. Thereby, it is necessary
to adapt the teaching to each student particular
needs. It is commonly agreed that, for adaptation,
some kind of student representation is needed. One
of the most common mechanisms to represent the
state and evolution of student learning are Student
The present works deals with the representation
of the building knowledge in an autonomous
learning process with through: a) an open student
model; and b) a tool called SIENA, a student
conceptual map explorer and instrospection.
Student Models can help teachers and students to
pick up the learning characteristics of student and
his evolution during the learning process.
The goal of any Student Model is to collect the
information related to the student that influences in
his/her learning such as the level of knowledge, the
acquired skills, the learning objectives, the learning
preferences, etc.
Usually, in the traditional Student Model the
access to the data they contain is a problem. So, the
community of Artificial Intelligence in Education
has proposed the Open Student Model, where the
student representation is designed for allowing
inspection. This model allows the direct intervention
of students in the process of diagnosis, and that
permit to infer the knowledge that students has on
the learning-teaching domain (Dimitrova, 2002).
This type of student model can be inspected by:
a) the own student, b) his classmates and c) his
Moreno L., S. González C., J. González E., Popescu B. and L. Oliveira C. (2009).
In Proceedings of the First International Conference on Computer Supported Education, pages 452-455
DOI: 10.5220/0002006104520455
teachers (Bull&Nghiem, 2002). The fact that a
student can access to his own model, help him to
better understand which learning strategy is
following, because a new source of information is
available. With this source he can think about his
own learning Bull, S., McEvloy, A.T. & Reid, E.,
Systems building under this perspective allow
externalizing the student models, and in some cases,
providing mechanism to teachers and students, can
change the contents. The selection of an effective
mechanism of communication reduces problems of
understanding of the behaviour of student
(Dimitrova et al., 2002).
Student model and conceptual graphs are a
power tools to represent the knowledge. The
knowledge represented in a visual way is easier to
explore and understand. Cook y Kay (1994) was
pioneer in to mix text and conceptual trees based on
diagrams. Other approach of Dimitrova et al. (2002),
is the inspection and discussion of a student model
trough conceptual graphs (Rueda U; Larrañaga M;
Arruarte A; Elorriaga Jon A., 2004).
Taken into account these previous works, we
have developed a tool called SIENA, where the
Student Model is represented and where the
processes where each student can build his
knowledge about a particular domain, in this case
Computer Architecture.
SIENA stands for Sistema Integrado de Enseñanza-
Aprendizaje, and in English SCOMAX/SCOMIN:
Student Conceptual Map Explorer/Student
Conceptual Map Instrospection. It is a new tool to
provide the learning which is based on conceptual
maps, adaptive tests and a Progressive Inquiry (PI)
model (Leinonen, T., Virtanen, O., Hakkarainen, K.,
Kligyte, G., 2002; Morales, R., Pain, H. and Conlon,
T., 1999)
SIENA requires a conceptual map which is
exported from Compendium called Pedagogical
Concept Instructional Graph PCIG. It consists of a
map with an organization among the nodes which
are situated in the map in the order that the students
requires for its comprehension. The student can
visualize in the graph and the nodes his own state of
knowledge in real time.
This tool has two main objectives:
1.- To allow to the teachers to know the skills of
students about a subject.
2.- Self-evaluation of students in a autonomous
virtual learning.
SIENA was building to solve the problem related
to handling information flows in a knowledge-
building environment, making students more aware
of the nature of progressive inquiry process (Le
Mans, France. Mühlenbrock, M., Tewissen, F.,
Hoppe, H.U., 1998).
The pedagogical model of progressive inquiry
learning (PI model) was designed to facilitate
engagement in an in-depth process of inquiry and
expert-like working with knowledge.
The purpose of this tool was to develop and test
a new pedagogical tool helping students to gain on
more efficient meta-cognitive thinking by helping
students to raise important ideas from the knowledge
building, being more aware of the group common
activities and stage in the progressive inquiry
The idea was to give students some real-time
software tools helping them to make their own
interpretations of the process they are involved in.
The tool presents the contents and carries out a
test based on Bayesian networks among concepts
and questions in all the nodes of a conceptual map of
a subject. However, the questions in the adaptive
test follow the scheme of the PI model, in this way:
a) Setting up the Context:
questions about
problems to central conceptual principles of
the domain of knowledge in question or to
authentic, rich real-world problem situations
b) Presenting Research Problems:
questions or
problems that guide the process,
explanation-seeking why and how
c) Creating Working Theories:
hypotheses, theories or interpretations for
the problem being investigated, explication
and externalization of these intuitive
conceptions (through guiding students, for
instance, to write about their ideas).
d) Critical Evaluation
: to assess strengths and
the weaknesses of different explanations and
identify contradictory explanations, gaps of
knowledge, and limitations of the power of
intuitive explanation.
e) Searching Deepening Knowledge
: search for
new scientific information about the
f) Developing Deepening Problems
weaknesses or limitations, questions and
working theories often provide significant
guidance for inquiry.
All aspects of inquiry, such as setting up
research questions, searching for new scientific
information, constructing of one's own working
theories or assessing the explanations generated,
are to be shared with other inquirers. These is the
last phase of inquiry process, called “distributed
expertise”, and consist in explaining a problem
to other inquirers.
Advancement of inquiry can be substantially elicited
by relying on socially distributed cognitive resources
emerging through social interaction between the
learners, and collaborative efforts to advance shared
understanding (Hoppe, U.,1995). Through social
interaction, contradictions, inconsistencies and
limitations of a student's explanations become
available because it forces him or her to perceive
conceptualizations from different points of view.
For this reason, we are working on building a
model of group represented from the information of
the individual models, and with new information,
such us, solidarity in the development of tasks and
collaborations among students in the tasks carried
out on SIENA, dialogues, etc. So, with this new
model, will be possible visualize the interaction
among students, with four basic elements that
influence the formation of group: a) presence, in a
particular activity, b) identity, of students c)
interaction, among students y d) communication
(Zapata-Rivera, J. and Greer, G., 2000; Rueda, U.,
Larrañaga, M., Arruarte, A., Elorriaga, J.A., 2003).
Bull. S. and Nghiem, T. (2002). “Helping Learners to
Understand Themselves with a Learner ModEl Open
to Students, Peers and Instructors”. Brna P. and
Dimitrova, V. (Eds.), Proceedings of Workshop on
Individual and Group Modelling Methods that Help
Learners Understand Themselves, ITS2002, pp. 5-13.
Dimitrova (Eds.), Proceedings of Workshop on Individual
and Group Modelling Methods that Help Learners
Understand Themselves, ITS2002, pp. 14-25.
Dimitrova, V., Brna P. and Self, J. (2002). The Design and
Implementation of a Graphical Communication
Medium for Interactive Learner Modelling. In
Proceedings of International Conference of Intelligent
Tutoring Systems ITS’2002, pp. 432-441.
Kay, J. (2001). “Learner Control”. User Modelling and
User-Adapted Interaction, Vol. 11, pp. 111-127.
Leinonen, T., Virtanen, O., Hakkarainen, K., Kligyte, G.
(2002). Collaborative Discovering of Key Ideas in
Knowledge Building. Proceedings of the Computer
Support for Collaborative Learning 2002 Conference.
Boulder, Colorado, USA, January 7-11, 2002.
Bull, S., McEvloy, A.T. & Reid, E. (2003). “Learner
models to promote reflection in combined desktop
PC/Mobile intelligent learning environments”. Bull,
S., Brna, P. And Dimitrova, V. (Eds.), Proceedings of
the Learner Modelling for Reflection Workshop,
Cook, R. and Kay, J. (1994). The justified user model: A
viewable, explained user model. In Fourth
International Conference on User Modelling, pp. 145-
150. The MITRE Corporation, Hyannis, MA.
Golstein, I.P. (1982). “The Genetic Graph: a
representation for the evolution of procedural
knowledge”. Sleeman, D. and Brown, J.S. (Eds.),
Intelligent Tutoring Systems, Academic Press, pp. 51-
Hoppe, U. (1995). “The use of multiple student modelling
to parametrize group learning”. Greer, J. (Ed.),
Proceedings of World Conference on Artificial
Intelligence in Education, pp. 234-241.
Larrañaga, M., Rueda, U., Elorriaga, J.A., Arruarte, A.
(2002). “Using CM -ED for the Generation of
Graphical Exercises Based on Concept Maps”.
Proceedings of ICCE’2002, pp. 173-177.
Larrañaga, M., Rueda, U., Elorriaga, J.A., Arruarte, A.
(2003). “A multilingual concept mapping tool for a
diverse world”. Proceedings of IEEE International
Conference on Advanced Learning Technologies
ICALT’2003, pp. 52-56.
Morales, R., Pain, H. and Conlon, T. (1999). “From
behaviour to understandable presentation of learner
models: a case study”. In Proceedings of the
Workshop on Open, Interactive, and other Overt
Approaches to Learner Modelling, AIED’99.
Le Mans, France. Mühlenbrock, M., Tewissen, F., Hoppe,
H.U. (1998). “A framework system for intelligent
support in open distributed learning environments”.
International Journal of Artificial Intelligence in
Education, Vol. 9, 256-274. Novak, J.D. (1977). A
theory of education, Ithaca, NY: Cornell University.
Rueda, U., Larrañaga, M., Arruarte, A., Elorriaga, J.A.
(2003b). “Study of graphical issues in a tool for
dynamically visualising student models”. Aleven, V.,
Hoppe, U., Kay, J., Mizoguchi, R., Pain, H., Verdejo,
CSEDU 2009 - International Conference on Computer Supported Education
F., Yacef, K. (Eds.), Suplementary Proceedings of the
International Conference on Artificial Intelligence in
Education AIED’2003, pp. 268-277.
Zapata-Rivera, J. and Greer, G. (2000). Inspecting and
Visualizing Distributed Bayesian Student Models.
Proceedings of International Conference of Intelligent
Tutoring Systems ITS’2000, pp. 544-553.