Vol.12 No.5 October 1, 2013
Semantic Web and Social Networks for E-learning

Editorial (pp361-362)
        Patricia Ordóñez de Pablos and Miltiadis D. Lytras

A Structural Approach to Extracting Chinese Position Relations from Web Pages (pp363-382)
        Peiquan Jin, Jia Yang, Jie Zhao, and Yanhong Liu
The use of position relations, which refer to the position of people in an organization, can serve for enterprises as a significant competitive intelligence method. The rapid growth of the data volume in the Web brings new opportunities for us to extract position relations of interest from the Web. In this paper, we propose a new algorithm to extract position relations from the Web. Our algorithm is based on the structural feature of position relations in the Web, i.e., a position relation is usually presented in Web pages as a table or a list. In order to define the structural feature of Web content, we first introduce a structural coefficient for each Web page, which is then used to generate structural file segments for Web pages. A structural file segment consists of all candidates of position relations having a similar structure. After that, we employ a pattern-matching method to extract position relations from the structural file segments. Finally, we conduct experiments on a real data set containing 6028 Chinese Web pages gathered by the Baidu search engine, and evaluate precision and recall of our approach. The experimental results confirm that our algorithm has a precision over 96% and a recall over 87%.

Using Hybrid Semantic Information Filtering Approach in CoPEs (pp383-402)
        Lamia Berkani, Azeddine Chikh, and Omar Nouali 
The paper discusses the application of the Information Filtering (IF) approach in Communities of Practice of E-learning (CoPEs). We identify the main characteristics of CoPEs and show how the integration of the IF techniques can be useful in this context as a technology support for members of CoPEs. A personalized recommendation approach is proposed for CoPEs based on the hybrid semantic IF, integrating the content-based filtering, the collaborative filtering and the ontology-based filtering approaches. Three strategies of recommendation have been proposed: (1) a semantic recommendation by specialty; (2) a semantic content-based recommendation by domains of interests; and (3) a semantic collaborative recommendation by domains of interests. We have developed a prototype of a recommendation system called ReCoPESyst, based on the recommendation approach. In order to evaluate our system, we considered a community of teachers from a higher education context. A preliminary tests and experimentation of ReCoPESyst conducted within this community show its advantage and benefit for members.

SemGsearch: An Approach to Semantically Retrieve Geospatial Objects from Different Geographic Servers (pp403-421)
        Julio Vizcarra, Miguel Torres, Rolando Quintero, and Marco Moreno-Ibarra
In this paper, we propose an approach to semantically retrieve geospatial objects within an Intranet by means of their metadata. It consists of structuring a semantic repository in order to provide the inclusion mechanisms of distributed data to be retrieved, as well as the extraction of those geospatial objects with respect to their conceptual similarity. The similarity measure is based on a conceptual distance (DIS-C algorithm), which consists of determining the levels of similarity among the objects for aiding in the construction of an engine of inclusion and extraction of them. This approach provides a mechanism to handle the knowledge of the geospatial objects distributed on different servers in order to unify the process by means of their semantics. As case study, a web-mapping application called SemGsearch has been designed. It provides to the user an engine of semantic retrieval and integration. The result is focused on obtaining a weighting list (ranking) of geospatial objects semantically retrieved by a custom query.

A Framework for Detecting and Removing Knowledge Overlaps in a Collaborative Environment (pp422-438)
        Maria Vargas-Vera and Miklos Nagy, and Patricia Ordonez de Pablos
This paper presents a framework for knowledge integration based on mappings between similar concepts in constraint graphs associated to a configuration problem. In particular, the paper deals with one of the problems which could arise when performing collaborative knowledge integration, namely detecting knowledge overlaps. The solution to the overlapping problem relies on the use of matching algorithms embedded in DSSim (short for Dempster-Shafer Similarity). To illustrate the approach, a case study of a computer configuration problem is presented. The solution to the knowledge overlap problem is important as it has the promise to become an alternative approach for the current knowledge integration solutions. Through our approach the real cost of integration can be reduced as it is not necessary to invest a great amount of resources beforehand a truly integrated system can be operational.

Semantic Web for Supporting Personal Work and Learning Environment Creation (pp439-456)
        Giuseppina Rita Mangione, Francesco Orciuoli, Pierluigi Ritrovato, and Saverio Salerno
The ARISTOTELE European project investigates the concept of the Personal Work and Learning Environment (PWLE), an approach allowing workers, seen as "lifelong learners", to benefit from - and contribute to - collective knowledge within their organization. The PWLE is a personal digital environment assisting workers in their knowledge cycle. Specifically, the PWLE makes it easy to transform workers’ tacit knowledge into explicit knowledge, and helps them contribute to collective knowledge that they can exploit for learning and work purposes. By facilitating the modeling, representation and accumulation of collective knowledge, Semantic Web technologies sustain PWLE processes in support of continuous learning in enterprises.

Back to JWE Online Front Page