Mihaela Brut

A personalized recommendation framework based on cam and document annotations

This paper presents a solution for recommending documents to students according to their current activity that is tracked in terms of semantic annotations associated to the accessed resources. Our approach is based on an existing tracking system that captures the user current activity, which is extended to build a user profile that comprises his/her interests in term of ontological concepts. A recommendation service is elaborated, implementing an algorithm that is alimented by Contextualized Attention Metadata (CAM) comprising the annotation of documents accessed by learners. The user profile is updated as soon as an activity is completed; thus, recommendations provided by the service are up-to-date in real time. The original aspect of this recommendation approach consists in combining a user activity tracking system with the exploitation of the semantic annotations associated with resources.

Enhancing the Knowledge Management Support within the E-Learning Platforms

In this paper we discuss and propose certain opportunities provided by the semantic Web technologies in the view of improving the learning content management. In order to express each metadata in the most appropriate metadata standard format, there could be integrated the general metadata standards elements and properties into e-learning standards (by replacing the existing elements or by being added to), and also use some appropriate high- level ontologies and domain ontologies in order to annotate the concepts inside the learning Objects. A good learning content management involves its correlation with the concrete students need and for this reason it implies also a good user profile management and a strong user community support.

A Generic Metadata Framework for the Indexation and the Management of Distributed Multimedia Contents

Currently, many multimedia contents are acquired and stored in real time and on different locations. These contents are indexed in order to provide some metadata that are used during the retrieval process. However, several existing metadata standards can be used for describing the content, and mixing them do not ensure interoperability. To overcome this problem, we propose in this paper a generic metadata framework that defines an abstract representation of a multimedia document and encapsulates the most common metadata standards.

A Competency-Oriented Modeling Approach for Personalized E-Learning Systems

In order to optimize the information retrieval and adaptation facilities inside an e-learning system, there is necessary to improve accessibility and to correlate the educational materials, the users and the information. For this purpose, we present a semantic Web-based modeling approach for the materials annotations and user competences profile, based on the same domain ontology set. The ontologies constitute thus the binder between the materials and users, and we illustrate how their reasoning support contributes to the efficiency improvement of the search and adaptive Web services. As illustrative example, we present our developed I*Teach Web repository of educational scenarios.

A Framework for Automatizing and Optimizing the Selection of Indexing Algorithms

Inside an information system, the indexation process facilitates the retrieval of specific contents. However, this process is known as time and resource consuming. Simultaneously, the diversity of multimedia indexing algorithms is growing steeply which makes harder to select the best ones for particular user needs. In this article, we propose a generic framework which determines the most suitable indexing algorithms according to user queries, hence optimizing the indexation process. In this framework, the multimedia features are used to define multimedia metadata, user queries as well as indexing algorithm descriptions. The main idea is that, apart from retrieving contents, user queries could be also used to identify a relevant set of algorithms which detect the requested features. The application of our proposed framework is illustrated through the case of an RDF-based information system. In this case, our approach could be further optimized by a broader integration of Semantic Web technologies.

An Ontology-Based Modeling Approach for Developing a Competencies-Oriented Collective Intelligence

Expressing the user competences through domain ontology concepts is a prerogative for developing well managed and semantically enriched user profiles, transferable from a system to another. If, supplementary, the available documents are also ontology-based annotated, the add-on value will concern not only the document semantics, but also the relations and dependencies between users and documents. In such approach, the ontology constitutes the binder between peoples, as well as between peoples and documents, and also between documents. Its reasoning support sustains the development of a collective intelligence, as well as the most suitable knowledge sharing, according to the users common competencies. In this article we present such modeling approach, and also some methods for user and document model development, as well as the advantages for personalized and collaborative facilities.

A Rule-Based Approach for Developing a Competency-Oriented User Model for E-Learning Systems

The present paper exposes a two layer user model (competences and interests) expressed through ontological constructs. As well, the paper illustrates a rule-based solution for developing the user profile in the context of the e-learning systems. The user model was conceived in the view of providing the users of an e-learning system with personalized functionalities, especially with recommendations on potential collaborators.

An ontology-based approach for providing multimedia personalised recommendations

This paper provides a service-oriented solution that explores the ontology-based modelling of users and documents in order to provide users with personalised recommendations of resources. Alongside the adoption of semantic web technologies for ontology-based modelling, our approach aims at a better relevance for recommendations by adopting a hybrid recommendation technique, combining a collaborative filtering and a content-based approach. The collaborative filtering module adopts a Markov Decision Process (MDP) in order to predict the next concept which will be focused on by the user, tracking the user navigation through an ontology instead of through the structure of a particular site. The content-based recommender module adopts a k nearest neighbours approach and exploits the similarities between the user and document modelling.

Ensuring Semantic Annotation and Retrieval within Pervasive E-Learning Systems

In the age of mobility, many times a certain teacher, a student or a document face difficulties to be integrated in different e-learning systems. Focusing on the computer science field, we present a service-oriented solution for annotating and retrieving the documents and persons involved in this domain, enhancing their mobility inside pervasive e-learning systems. The solution is based on the ACM classification system, which is used in order to develop user competence profiles, to annotate materials, and to retrieve them. The ontology-based retrieval mechanism will investigate not only the matches with the concepts involved in a query, but also with their related concepts inside the ACM classification system; the ranking algorithm will consider the documents content as well as the user competence.

Ontology-based flexible topic classification of crowdsourcing textual resources

The paper presents a solution to the problem of capitalizing in different contexts and by different stakeholders the time-stamped new documents produced by social Web sites (including news, blog entries, and uploaded documents). The solution core includes an ontology-based method to express the interest topics and to automatically classify them. For such textual content obtained in real-time, we propose an unsupervised text classification system based on general YAGO ontology, graph algorithms and a custom scoring method. The system shows good performance using only ontology information and the ontology structure itself. We compare our system against a SVM-based (Support Vector Machine) classic text classification approach. For determining the relevance of a specific document for a specific topic, our approach develops and compares the ontology sub graphs corresponding to the query and to the document. It leads to a high flexibility in terms of capitalizing the already classified documents when refining and changing the interest topic: a graph-based matching of the already obtained ontology-based document representation against the new query representation is enough to assess the document relevance.