Ebook: Semantic Web Technologies for e-Learning

Recent research on web-based educational systems attempts to meet the growing needs and expectations of the education community concerning e-learning efficiency, flexibility, and adaptation by employing ontologies and Semantic Web standards and paradigms. These advanced technologies allow for more intelligent access and management of web information and semantically richer modelling of content, applications, and users. Within the educational field, they motivate efforts to achieve semantically rich, well-structured, standardised, and verified learning content and learning activities that can be shared and reused by others. Conceptualizations, ontologies, the available W3C standards such as XML, RDF(S), OWL, OWL-S and educational standards such as LOM, SCORM, and IMS-LD allow specification of components in a standard way. The standards-based machine-processable semantic descriptions of web resources provide the necessary ground for achieving reusability, shareability, and interoperability of educational web resources and better personalization in educational hypermedia and web-based applications.

The notion of Social Semantic Web describes an emerging design approach for building Semantic Web applications which employs Social Software approaches. Social Semantic Web systems usually support collaborative creation, usage and continuous refinement of Semantic Web structures by communities of users. Typically they elicit domain knowledge through semi-formal ontologies, taxonomies or folksonomies. Semantic Web and Social Semantic Web techniques offer new perspectives on intelligent educational systems by supporting more adequate and accurate representations of learners, their learning goals, learning material and contexts of its use, as well as more efficient access and navigation through learning resources. They advance the state-of-the-art in intelligent educational systems development, so as to achieve improved e-learning efficiency, flexibility and adaptation for single users and communities of users (learners, instructors, courseware authors, etc.).

Within this context, this book attempts to outline the state-of-the-art in the research on application of ontologies and Social and Semantic Web technologies in e-Learning. It presents a view of the latest theoretical and technological advances, various perspectives of application of Semantic Web and Web 2.0 technologies in e-Learning, and showcases major achievements in this area. Most of the chapters present research and applications stemming out of work reported at the recent editions of the International Workshop on Ontologies and Semantic Web in e-Learning (SWEL).

http://compsci.wssu.edu/iis/swel/.

The book is aimed as a guide for researchers and developers to gain understanding of the present and future tendencies in the research in this field. It consists of three parts, the first concentrating on Ontologies, the second on Technologies, and the third on the emerging Social Semantic Web. Within these sections of the book, viewpoints and research findings of various authors are organized. The book cannot claim to cover the full breadth of issues in the SWEL domain, but opens up a number of interesting issues and leaves many open problems for future researchers to pursue.

In the first part, ontologies in support of e-Learning are examined, stretched, evaluated, and applied. Rogozan and Paquette tackle the challenging problem of ontology evolution, explaining how ontologies change over time and providing a mechanism and an ontology for describing this evolution. Dicheva and Dichev attack the practical problem of scaling up learning content repositories, pushing the limits of ontological representation schemes. Lillian Cassel investigates the “ontology of all computing” and the efforts of the ACM and others in the process of curriculum mapping based upon a comprehensive ontology of concepts. Three chapters investigate the practical problems of applying ontologies directly to authoring instruction for learners. Mizoguchi et al. look at ontologies underlying instructional and learning theories, formulating such theories into representational and reasoning engines suitable for authoring content. Suraweera et al. focus on ontology support for authoring constraint-based tutors, demonstrating the generality of an ontological approach in automating the development of domain models. Finally, Soldatova and Mizoguchi apply ontologies to the development of assessment examinations.

The second part of this book surveys selected areas among the vast set of possibilities for application of Semantic Web technologies to e-learning. Jovanovic et al. demonstrate how instructor feedback can be enhanced with Semantic Web technologies. Libbrech and Desmoulins improve content annotation, representation and searching in a Geometry teaching domain. Melis et al. describe how semantic technologies have been incorporated in ActiveMath, an intelligent tutoring system that has been enhanced with Semantic Web technologies. Radenković et al. present enhancements to generalized testing and assessment systems, while Pasin and Motta present a Semantic Web tool tightly bound to the discipline of Philosophy. And finally, Dzbor and Rajpathak present a Semantic Web-enhanced general platform for search and aggregation of information about authors and content topics.

The third and final part of the book speaks to the developing technologies related to the Social Semantic Web. Jovanovic et al. survey this emerging area. Brooks et al. present a number of projects and experiences that broadly explore Semantic Web technologies in social learning contexts. To conclude this volume, Loll and Pinkwart offer a new approach to collaborative filtering that relies on Semantic Web technologies.

Current research on the application of ontologies and Semantic Web technologies in e-Learning covers an even greater scope that this diverse set of articles might suggest. Though we provide a selective view of the emerging research, we want to convey a sense of today's cutting edge in the design, implementation, and evaluation of ontology-aware web-based educational environments and community-centred educational social applications. We hope that this book will provide some new insights and serve as a catalyst to encourage others to investigate the potential of the application of ontologies and Social and Semantic Web technologies for their organisational needs and research endeavours.

Darina Dicheva, Winston-Salem State University, USA

Riichiro Mizoguchi, Osaka University, Japan

Jim Greer, University of Saskatchewan, Canada

Because ontologies evolve over time, their evolution needs to be managed. Therefore, in this paper, we propose a framework composed of two main systems: ChangeHistoryBuilder, which tracks and manages the history of ontology changes, and SemanticAnnotationModifier, which provides a support to maintain the integrity of the ontology-based referencing of resources after the ontology evolution. Both systems are based on a formal specification of types of possible changes in OWL-DL ontologies. In concrete terms, this specification is an ontology of ontology changes.

We propose an environment that enables authors to create learning repositories by collecting and annotating learning content using a consensually agreed vocabulary and learners to explore the repositories based on relevant staring points for exploration. The authors' support includes: (i) tools for creating an ontological structure, partially populated with learning resources, to be used as a skeleton for structuring and organizing course related resource repositories, and (ii) help in selecting names for new concepts/topics combined with their subject identification. Besides the conventional querying and browsing support for learners, the focus is on tasks that imply exploratory search requiring extensive navigation on the part of the user. In this context we propose a method for finding good staring points for navigation designed to assist learners in performing open-ended search tasks in learning repositories.

The computing disciplines have a long history of curriculum recommendations developed and disseminated by the education committees of relevant societies. The process has become unmanageable as the disciplines become more diverse and the field expands. Recent work on an ontology of all computing offers a possibility of a new approach to curriculum development, both at the society level and for individual departments, by providing a comprehensive and objective view of the entire discipline. This chapter presents the motivation for an ontology-driven curriculum process and a preliminary plan for its use.

At one time, computers that could understand learning and instructional theories seemed only a dream, yet recent advances in ontological engineering have enabled this dream to come true. We first envisioned such a goal in 2000, to be realized in 2010 [16]. Since then, we have tackled this problem and devised a theory-aware authoring system named SMARTIES, based on a comprehensive ontology of learning and instructional theories named OMNIBUS. This chapter discusses the philosophy behind the research as well as its technological details.

In this chapter we focus on the role of ontologies in developing constraint-based tutors, a special class of Intelligent Tutoring Systems (ITSs). Domain models for ITSs are extremely difficult to develop, and therefore efforts devoted to automatic induction of the necessary knowledge are of critical importance for widening the real-world impact of ITSs. We conducted an initial study which showed that ontologies were useful for manual composition of domain models for constraint-based tutors, as they allow authors to reflect on their understanding of the domain and organize the domain model better. Starting from these encouraging results, we developed ASPIRE, an authoring system for constraint-based tutors, which automated many of the tasks in domain model generation and serves the produced ITSs. The domain ontology plays a central role in the authoring procedure deployed in ASPIRE. We present one of the ITSs produced in ASPIRE as well as the experiences of authors in using ASPIRE.

This chapter proposes: an ontology for the development of tests, the architecture of a test generation module (as a part of a learning management system), and a test generation system (as a separate information system). As an example of the proposed ontology engineering approach to the development of test generation systems we describe an implemented semi-automatic system capable of: designing and generating tests, assisting a user in defining input test parameters (for example a test goal, a scoring schema), explaining the test generation process, and producing test specifications. The system has been tested in two Universities: Aberystwyth (UK), and Vladivostok (Russia).

The chapter presents our research aimed at providing teachers with fine-grained and contextualized feedback about students' activities in online learning environments. The rational is that teachers provided with such advanced feedback are able to better organize/revise the course content and customize that content to the students needs. Our approach is based on semantic technologies, namely ontologies and semantic annotation, which enable integration of data about students' interactions with e-learning environments, as well as interlinking of learning artifacts that were used or produced during those interactions. We have implemented this approach into a tool called LOCO-Analyst and first applied it in Learning Content Management Systems (LCMSs) as today's most often used e-learning environments. Subsequently, we further enhanced this approach (as well as the LOCO-Analyst tool) to leverage the features of advanced e-learning settings, i.e. LCMSs extended with tools for enhanced learning experience. In particular, we have studied the benefits for educational feedback provisioning that stem from integrating tools for collaborative content annotation (such as tagging, highlighting and commenting) into LCMSs. This enabled us to provide teachers with course ontology maintenance and evolution features.

Interactive Geometry is becoming part of the curriculum in many European countries; sharing the files of interactive geometry, the constructions, is, however difficult because of the communities are scattered between the many software systems and the many curriculum differences. The Intergeo project addresses this issue by offering a platform where cross-curriculum search and annotation can be done. The annotation language is an ontology and is made easily accessible to users; this ontology describes elementary competencies and topics and their relationships. The search functions, the management, and the access are all empowered by the semantic nature of this ontology together with the various names attached to each ontology element. This paper describes the ontology and the infrastructure that provides utility, usability, and interoperability to this knowledge corpus.

ACTIVEMATH is an intelligent e-Learning platform that exhibits a number of Semantic Web features. Its content knowledge representation is a semantic XML dialect for mathematics, semantic search is enabled, some of its components work as a web service and, vice versa, it employs certain foreign web services, e.g., for diagnostic purposes.

This chapter presents the development of a computer assisted intelligent assessment system. The system is based on the IMS QTI standard and designed by applying the Model Driven Architecture (MDA) software engineering standards, the artificial intelligence and description logic reasoning techniques based on tableau algorithm. The chapter, also, shows the use of metamodel transformations between concrete languages. We propose the framework for assessment system that is reusable, extensible, and facilitates interoperability between its component systems. Also the chapter defines the consistency of test.

As the Semantic Web is increasingly becoming a reality, the availability of large quantities of structured data brings forward new challenges. In fact, when the content of resources is indexed, not just their status as a text document, an image or a video, it becomes important to have solid semantic models which avoid as much as possible the generation of ambiguities with relation to the resources' meaning. Within an educational context, we believe that only thanks to these models it is possible to organize and present resources in a dynamic and contextual manner. This can be achieved through a process of narrative pathway generation, that is, the active linking of resources into a learning path that contextualizes them with respect to one another. We are experimenting this approach in the PhiloSurfical tool, aimed at supporting philosophy students in understanding a text, by presenting them ‘maps’ of relevant learning resources. An ontology describing the multiple aspects of the philosophical world plays a central role in this system. In this chapter we want to discuss some lessons-learned during the modeling process, which have been crystallized into a series of reusable patterns. We present three of these patterns, showing how they can support different context-based reasoning tasks and allow a formal conceptualization of ambiguities that are primarily philosophy-related but can be easily found in other domains too. In particular, we describe a practical use of the ontology in the context of a classic work in twentieth century philosophy, Wittgenstein's Tractatus Logico-Philosophicus.

Work reported in this chapter focuses on the learner's interaction with resources on the Semantic Web; in particular with the semi-structured data that can be exposed to the user via domain-specific inference templates. We assessed this capability to use information from multiple sources of the service-based ASPL-v2 framework and analyzed it in terms of assisting users with interpreting connections in the academic domain; for example, identifying leading experts, recognizing communities of practice, or associating research topics and issues with particular publication outlets. The outcomes of a user-based study are reported, with our semantic platform found to outperform other similar tools – including the generic search engine aggregator Ask and semi-specialized Google Scholar.

The Social Semantic Web has emerged recently as a new paradigm for creating, managing and sharing information through the combined use of technologies and approaches from the Social Web (aka Web 2.0) and the Semantic Web. In this chapter, we first introduce the fundamental concepts of the Social Semantic Web. Subsequently, we focus on (some of) the benefits that the Social Semantic Web paradigm can bring to e-learning environments, such as effective and reliable knowledge management and sharing, advanced forms of interactivity and ubiquitous access to learning resources.

This paper describes work we have done over the past five years in developing e-learning applications and tools using Semantic Web and Web 2.0 technologies. It does not provide a comprehensive description of these tools; instead, we focus on the pitfalls we have encountered and attempt to share experiences in the form of design patterns for developers and researchers looking to use these technologies.

Today, collaborative filtering techniques play a key role in many Web 2.0 applications. Currently, they are mainly used for business purposes such as product recommendation. Collaborative filtering also has potential for usage in “Social Semantic Web” e-learning applications in that the quality of a student provided solution can be heuristically determined by peers who review the solution, thus effectively disburdening the workload of teachers and tutors. This chapter presents a collaborative filtering algorithm which is specifically adapted for the requirements of e-learning applications. An empirical evaluation of the algorithm showed that the results of the collaborative filtering were more accurate than the self-assessment of the participants and that already four peer evaluations were generally enough to reach a satisfying accuracy. Based on these results, we developed a web based e-learning system (CITUC), which was successfully used in a university course in summer 2008. This chapter describes an evaluation of CITUC based on surveys, interviews and a detailed analysis of the system's usage by students. Our conclusion is that Social Semantic Web applications such as CITUC, which enable learners to review and comment on peer solutions, have high potential as a support for classic academic teaching in larger classes.