سیستم های پیشرفته مدیریت هستی شناسی برای آموزش الکترونیکی شخصی شده

The use of ontologies to model the knowledge of specific domains represents a key aspect for the integration of information coming from different sources, for supporting collaboration within virtual communities, for improving information retrieval, and more generally, it is important for reasoning on available knowledge. In the e-Learning field, ontologies can be used to model educational domains and to build, organize and update specific learning resources (i.e. learning objects, learner profiles, learning paths, etc.). One of the main problems of educational domains modeling is the lacking of expertise in the knowledge engineering field by the e-Learning actors. This paper presents an integrated approach to manage the life-cycle of ontologies, used to define personalised e-Learning experiences supporting blended learning activities, without any specific expertise in knowledge engineering.

Knowledge modeling represents a significant activity, that is particularly difficult to perform due to its complexity. Nowadays, in computer and information science, knowledge representation, reuse and sharing are facilitated by the explicit use of ontologies. In [1], an ontology is an “explicit specification of a conceptualization”. The term is borrowed from philosophy, where an ontology is a systematic account of existence. For artificial intelligence systems, what exists is what can be represented. Pragmatically, a common ontology defines the vocabulary with which queries and assertions are exchanged among agents. Agents can be both software agents and/or human agents. Recently, we have seen an explosion of interest in ontologies as artifacts to represent human knowledge and as critical components in knowledge management, Semantic Web, business-to-business applications, and several other application’s areas. Also in the e-Learning area there is a newly great interest in the exploitation of knowledge technologies. Most of the current learning technology specifications are based on educational metadata: IEEE LOM [2] and ADL SCORM [3], for example, are the standards proposed for describing (and re-using) chunks of learning content annotated through metadata. Metadata is supposed to enable the reuse of these chunks by detailing the conditions of their initial deployment. However, the authors of [5] and [4] pointed out that such an approach failed to elicit cognitive behaviours and therefore the actual reuse. We believe that the use of ontologies in e-Learning can overcome these drawbacks. In [6], some benefits from applying ontologies to e-Learning are well explained. The authors asserts that an ontology, formally and declaratively, represents the terminology of a specific domain, defining its essential knowledge. Ontologies are used to support semantic search, making possible to query multiple repositories and discover associations, between learning objects, that are not directly understandable. This is impossible or very complex with simple keyword- or metadata-based search supported by the current standards. In this paper, we describe methodologies and techniques for supporting a community of experts in modeling educational domains (e.g. mathematics domain, English literature domain, etc.) through the management of convenient educational ontologies namely e-Learning ontologies and exploiting them in order to define and execute personalised e-Learning experiences within blended learning activities. Blended learning is considered a learning approach defined by the effective combination of different modes of delivery and models of teaching and styles of learning [7]. Personalised e-Learning experiences represent a convenient way to complement face-to-face sessions within a whole blended learning experience. A personalised e-Learning experience could be very important when used for assessing the knowledge acquired by each individual learner during a face-to-face learning session and offering, in case of negative results, personalised remedial works able to fill the identified knowledge gaps with learning paths that best fits the needs, the cognitive state and the learning preferences of each individual learner. In the event that the personalised e-Learning experience can be built, packaged and deployed with an automatic process, then the whole blended learning activity can become more effective and efficient. Anyway, knowledge modeling through ontologies is a subjective process essentially, whereby different people that model the same domain, produce, in most cases, different ontologies depending on their sensitivity, their background, etc. In a distributed environment, such as communities of experts, harmonizing the work of all parties can be a relevant activity, in order to enrich and improve the available knowledge bases. For these reasons, we define a set of convenient techniques for versioning and harmonization of e-Learning ontologies. The current methodologies, developed in the e-Learning domain do not allow the integrated management of knowledge that meets all the requirements above mentioned. The proposed approach is conceived to allow the collaborative and shared management of the available knowledge, without having any specific proficiency in knowledge engineering taking into account aspects like ontology harmonization and ontology versioning. In particular, we focus on the collaboration approaches for ontology building and maintenance. More precisely, the most relevant contributions of our work are: • The definition of convenient models to represent and exploit e-Learning ontologies in order to build and deliver personalised e-Learning experiences taking into account different cognitive states and learning preferences of learners. • The definition of a set of tools for representing and managing e-Learning ontologies, within a community of teachers, tutors, mentors, etc. (without any expertise of knowledge engineering) through the features of an integrated framework; The paper is organized as follows: Section 2 presents some related works; in Section 3 we describe our approach to build personalised e-Learning experiences through the use of ontologies; in Section 4 we describe the algorithms and the techniques to manage the life-cycle of e-Learning ontologies through our advanced ontology management system; in Section 5 a case study of an AOMS collaborative ontology construction session is presented. Finally, Section 6 concludes the work.

In this work we have proposed an approach for the educational domain modeling through the use of ontologies. We have described in details how to construct e-Learning ontologies and how they are exploited in order to define and execute personalised e-Learning experiences. The personalization allows to execute more efficient and effective e-Learning processes. The approach is fully implemented into a commercial e-Learning platform, namely IWT. Further improvements have been thought, designed and prototyped in the context of ELeGI UE Integrated Project [39] from the delivery infrastructure (based on Grid Technologies) and the pedagogical (several educational methods are implemented in order to enrich the IWT e-Learning experiences) points of view. The necessity to improve knowledge management aspects, with more features, tools and methodologies, comes from the results of numerous experimentation cases carried out using the IWT platform. Therefore, investigating the state of the art of Semantic Web, with respect to ontology management, and experimenting existing software tools we have matured the following ideas: • We cannot force the e-Learning actors to have knowledge engineering competencies and use complex existing tools. Then, a visual, drag and drop based, and user-centric ontology editing technique has been defined. • If we want to really exploit the potentiality of personalised e-Learning, also within blended learning processes, we have to help the e-Learning actors to effectively reuse knowledge and manage inconsistencies due to the knowledge natural evolution. Then, ontology harmonization, versioning and changes tracking techniques have been defined. • Ontology development is often a collaborative process. Furthermore, it can be very difficult to use these tools without competencies in knowledge engineering. Then, a collaborative ontology construction technique has been defined. The technique foresees the exploitation of a workflow engine in order to support the tasks coordination. The technique provides a validation phase based on a semantic wiki engine allowing the collaboration participants to reach a consensus about the final ontology. Without the validation phase there is no assurance that all participants agree with the final artifacts. Conversely, using only the semantic wiki engine in order to construct the ontology does not satisfy the simplified task coordination requirement. Future works will consist of other validation and testing activities in order to improve the potentiality of Semantic Web in the e-Learning area.