Conference Paper

An Ontological Approach for Semantic-Aware Learning Object Retrieval.

DOI: 10.1109/ICALT.2006.1652407 Conference: Proceedings of the 6th IEEE International Conference on Advanced Learning Technologies, ICALT 2006, 5-7 July 2006, Kerkrade, The Netherlands
Source: DBLP


SCORM LOM (sharable courseware object reference model learning object metadata) , enables the indexing, location, management, and searching of learning objects in a learning object repository by extended sharing and searching features. However, LOM has a deficiency in semantic-awareness capability. In most information retrieval systems, users' cognitive ability on what they need is a basic system assumption. However, in e-learning systems, users may have no idea on what they want and what the learning objects' metadata is. This paper presents an ontological approach for semantic-aware learning object retrieval. This approach is generic enough to be embedded to other LOM-based search mechanisms to achieve semantic-aware learning object retrieval

11 Reads
  • Source
    • "In AEHS, these keywords are defined over the domain concept ontology during the concept selection process, as already discussed . In this case, the ranking of LOs is performed using a concept/keywordbased similarity formula (Lee et al. 2006, Biletskiy et al. 2009), which evaluates the relevance of each LO, by comparing the desired concepts/keywords with the classification metadata used for describing the LO in hand. The main assumption of this approach is that the domain concept ontology and the classification metadata used for the LOs share the same concept/keyword terms. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Adaptive content selection is recognized as a challenging research issue in adaptive educational hypermedia systems (AEHS). In order to adaptively select learning objects (LOs) in AEHS, the definition of adaptation behavior, referred to as Adaptation Model (AM), is required. Several efforts have been reported in lit-erature aiming to support the AM design by providing AEHS designers with either guidance for the direct definition of adaptation rules, or semi-automated mecha-nisms which generate the AM via the implicit definition of such rules. The goal of the semi-automated, decision-based approaches is to generate a continuous deci-sion function that estimates the desired AEHS response, aiming to overcome the problems of insufficiency and/or inconsistency in the defined adaptation rule sets. Although such approaches bare the potential to provide efficient AMs, they still miss a commonly accepted framework for evaluating their performance. In this book chapter, we discuss a set of performance evaluation metrics that have been proposed by the literature for validating the use of decision-based approaches in adaptive LO selection in AEHS and assess the use of these metrics in the case of our proposed statistical method for estimating the desired AEHS response.
    Intelligent and Adaptive Educational-Learning Systems: Achievements and Trends, 01/2013: chapter 7: pages 161-182;
  • [Show abstract] [Hide abstract]
    ABSTRACT: There are a variety of specifications and metadata standards used to describe learning contents. A learning content, along with t he file containing the descriptive metadata, constitutes the learning object. Learning objects can be stored in a repository and used in the process of teaching and learning. The h eterogeneity of metadata standards used to describe learning objects creates difficulties t o reuse of these objects. Applications that seek to recover learning objects cannot interoperat e with different repositories, which contain objects described according to different me tadata standards. This paper proposes a multi-agent system, wherein agents can index and re trieve learning objects that are contained in different repositories and described w ith different metadata standards. These agents use an ontology that is the result of the un ion of all the ontologies that contextualize the existing metadata standards.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: With vigorous development of the Internet, especially the web page interaction technology, distant E-learning has become more and more realistic and popular. Digital courses may consist of many learning units or learning objects and, currently, many learning objects are created according to SCORM standard. It can be seen that, in the near future, a vast amount of SCORM-compliant learning objects will be published and distributed cross the Internet. Facing huge volumes of learning objects, learners may be lost in selecting suitable and favorite learning objects. In this paper, an adaptive personalized recommendation model is proposed in order to help recommend SCORM-compliant learning objects from repositories in the Internet. This model adopts an ontological approach to perform semantic discovery as well as both preference-based and correlation-based approaches to rank the degree of relevance of learning objects to a learner's intension and preference. By implementing this model, a tutoring system is able to provide easily and efficiently suitable learning objects for active learners. © International Forum of Educational Technology & Society (IFETS).
    Educational Technology & Society 07/2007; 10(3):84-105. · 1.01 Impact Factor
Show more


11 Reads
Available from