Using data mining techniques for exploring learning object repositories
| DOI | https://doi.org/10.1108/02640471111125140 |
| Date | 12 April 2011 |
| Published date | 12 April 2011 |
| Pages | 162-180 |
| Author | Alejandra Segura,Christian Vidal‐Castro,Víctor Menéndez‐Domínguez,Pedro G. Campos,Manuel Prieto |
| Subject Matter | Information & knowledge management,Library & information science |
Using data mining techniques for
exploring learning object
repositories
Alejandra Segura and Christian Vidal-Castro
Universidad del Bio-Bio, Concepcio
´n, Chile
Vı
´ctor Mene
´ndez-Domı
´nguez
Universidad Auto
´noma de Yucata
´n, Yucata
´n, Mexico
Pedro G. Campos
Universidad del Bio-Bio, Concepcio
´n, Chile, and
Manuel Prieto
Universidad de Castilla-La Mancha, Madrid, Spain
Abstract
Purpose – This paper aims to show the results obtained from the data mining techniques application
to learning objects (LO) metadata.
Design/methodology/approach – A general review of the literature was carried out. The authors
gathered and pre-processed the data, and then analyzed the results of data mining techniques applied
upon the LO metadata.
Findings – It is possible to extract new knowledge based on learning objec ts stored in
repositories. For example it is possible to identify distinctive features and group learning objects
according to them. Semantic relationships can also be found among the attributes that describe
learning objects.
Research limitations/implications – In the first section, four test repositories are included for
case study. In the second section, the analysis is focused on the most complete repository from the
pedagogical point of view.
Originality/value – Many publications report results of analysis on repositories mainly focused on
the number, evolution and growth of the learning objects. But, there is a shortage of research using
data mining techniques oriented to extract new semantic knowledge based on learning objects
metadata.
Keywords Data analysis,E-learning, Metadata, Data mining,Digital libraries
Paper type Research paper
1. Introduction
The increase in the amount of data generated by various human activities has required
the employment of techniques to analyze large volumes of data. These techniques have
the goal of extracting useful information from data for decision making. Among them,
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/0264-0473.htm
This work is partially supported by MECESUP UBB 0305 project, Chile; the National Council of
Science and Technology (CONACYT, Me
´xico); the Council of Science and Technology of
Yucata
´n State (CONCyTEY, Me
´xico); the TIN2007-67494 project of the Science and Innovation
Ministry; The PEIC09-0196-3018 project of the Autonomous Government of Castilla-La Mancha.
EL
29,2
162
Received 12 October 2010
Accepted 20 October 2010
The Electronic Library
Vol. 29 No. 2, 2011
pp. 162-180
qEmerald Group Publishing Limited
0264-0473
DOI 10.1108/02640471111125140
data mining (DM) techniques are used in many knowledge areas such as commerce,
biology, sociology, entertainment, although the main difference is the purpose in which
they are used. The application of DM techniques to the domain of e-Learning has
become more frequent in recent years (Romero et al., 2008). Data mining in e-learning
has been used in multiple problems, such as student’s learning assessment, learning
materials and course evaluation, and course adaptation based on students’ learning
behavior. Here we focus on analyzing the metadata stored inside learning object
repositories (LORs).
The LORs nowadays implement flexible mechanisms for the search and selection of
resources based on metadata or text matching (Broisin et al., 2005; McLean and Lynch,
2003). However, users of these repositories do not have an a priori clear view about the
kind of resources stored and to what extent they fit their interests or preferences. This
gap might be filled by extracting characterizations of learning objects obtained from
the analysis of their metadata. Besides, such characterizations could be used to
enhance search or to improve the descriptions of the content stored in repositories,
providing useful information for both humans and software applications.
Publications reporting results of analysis on repositories are mainly focused on the
amount, evolution and growth of learning objects (Ochoa and Duval, 2009). However,
there is a shortage of research using data mining techniques oriented to extract new
semantic knowledge based on learning objects metadata. For this study we used the
metadata base of the AGORA recommender system (Prieto et al., 2008) and other
already existing LORs. Clustering, classification, predictive attributes and association
rules techniques were selected to approach a first exploration of the characterization of
LORs. Concretely, the study reported here has aimed at providing some preliminary
insight on the following questions:
.What is the “status” of stored objects in terms to their completeness and
compliance with standard metadata?
.Are there any learning objects groups, which have similar characteristics in their
metadata?
.From the instructional point of view, which relations between the learning
objects metadata are the most significant?
The structure of the paper is described as follows. Section 2 shows general
antecedents related to this research. Section 3 details methodological issues and
describes the technical issues related to data gathering. Section 4 shows analysis and
applied DM techniques. Next, a discussion on obtained results is included in section 5.
Finally, the main conclusions of our research work as well as future work are
highlighted.
2. Background
The concept of e-learning resources has been formalized in the concept of learning
object (hereafter LO). Although there are many different definitions for LO, this study
will use the definition proposed by McGreal (2004): an LO is “any reusable digital
resource that is encapsulated in a lesson or assemblage of lessons grouped in units,
modules, courses, and even programmes. A lesson can be defined as a piece of
instruction, normally including a learning purpose or purposes” (McGreal, 2004, pp. 11).
The purpose of an LO is to provide a standards-based modular model that allows
Exploring
learning object
repositories
163
To continue reading
Request your trial