Hend S. Al-Khalifa

The evolution of metadata from standards to semantics in E-learning applications

Metadata attempts to describe the content, format, purpose and structure of data. Over the past few years, the IEEE-LOM standard has dominated the metadata world in e-learning applications. However, with the advent of the Semantic Web, e-learning applications are beginning to evolve their metadata representation from these standards by adding semantic structure or by converting entirely to semantic representations of structure. This shift enables the implementation of a range of new tools which can reason over the metadata, providing added value from the stored data. This review paper summarizes this evolution of metadata used in e-learning applications from standards to semantic representation.

Exploring the Value of Folksonomies for Creating Semantic Metadata

Finding good keywords to describe resources is an on-going problem: typically we select such words manually from a thesaurus of terms, or they are created using automatic keyword extraction techniques. Folksonomies are an increasingly well populated source of unstructured tags describing web resources. This paper explores the value of the folksonomy tags as potential source of keyword metadata by examining the relationship between folksonomies, community produced annotations, and keywords extracted by machines. The experiment has been carried-out in two ways: subjectively, by asking two human indexers to evaluate the quality of the generated keywords from both systems; and automatically, by measuring the percentage of overlap between the folksonomy set and machine generated keywords set. The results of this experiment show that the folksonomy tags agree more closely with the human generated keywords than those automatically generated. The results also showed that the trained indexers preferred the semantics of folksonomy tags compared to keywords extracted automatically. These results can be considered as evidence for the strong relationship of folksonomies to the human indexer’s mindset, demonstrating that folksonomies used in the del.icio.us bookmarking service are a potential source for generating semantic metadata to annotate web resources.

Towards better understanding of folksonomic patterns

Folksonomies provide a free source of keywords describing web resources; however, these keywords are free form and their semantics spans multiple contextual dimension. In this paper, we present a pragmatic experiment that analyzes folksonomies using three classification categories: Personal, Factual and Subjective, in order to gain more understanding of the types of tags used in the social tagging process. The rational for this work was to measure the potential portion of folksonomy tags that might be helpful when considering the creation of structured metadata.

Measuring the Semantic Value of Folksonomies

Semantic metadata, which describes the meaning of documents, can be produced either manually or else semi-automatically using information extraction techniques. Manual techniques are expensive if they rely on skilled cataloguers, but a possible alternative is to make use of community produced annotations such as those collected in folksonomies. This paper reports on an experiment that we carried out to validate the assumption that folksonomies carry more semantic value than keywords extracted by machines. The experiment has been carried-out in two ways: automatically, by measuring the percentage of overlap between the folksonomy set and machine generated keywords set; and subjectively, by asking a human indexer to evaluate the quality of the generated keywords from both systems. The result of the experiment can be considered as evidence for the rich semantics of folksonomies, demonstrating that folksonomies used in the delicious bookmarking service can be used in the process of generating semantic metadata to annotate Web resources

FolksAnnotation: A Semantic Metadata Tool for Annotating Learning Resources Using Folksonomies and Domain Ontologies

There are many resources on the Web which are suitable for educational purposes. Unfortunately the task of identifying suitable resources for a particular educational purpose is difficult as they have not typically been annotated with educational metadata. However, many resources have now been annotated in an unstructured manner within contemporary social bookmaking services. This paper describes a novel tool called `FolksAnnotation that creates annotations with educational semantics from the del.icio.us bookmarking service, guided by appropriate domain ontologies

Replacing the Monolithic LOM: A Folksonomic Approach

IEEE-LOM is a well-known metadata standard for describing learning resources. However, many problems are associated with this kind of representation, which include the number of fields to be filled and the amount of time needed to fill them. To overcome this hurdle, we propose the use of cheap unstructured metadata to create structured semantic metadata, this metadata is called folksonomy. In this paper we show an approach that uses folksonomy tags to create structured metadata using semantic web technologies. The generated folksonomic metadata are then evaluated against a human expert annotation.

FAsTA: a folksonomy-based automatic metadata generator

Folksonomies provide a free source of keywords describing web resources, however, these keywords are free form and unstructured. In this paper, we describe a novel tool that converts folksonomy tags into semantic metadata, and present a case study consisting of a framework for evaluating the usefulness of this metadata within the context of a particular eLearning application. The evaluation shows the number of ways in which the generated semantic metadata adds value to the raw folksonomy tags.

Delicious Learning Resources

This paper presents a novel approach to semantic annotation of learning resources using a blend of folksonomy keywords and ontology-based semantic annotation. This approach attempts to match folksonomy terms (after normalization), from bookmarked resources saved in a bookmarking service such as del.icio.us, against terms in the ontology (which operates as a controlled vocabulary). The approach will provide an attribute-value relationship that is semantically rich and adds ‘intelligence’ to search for learning resources in a specific subject domain.