Authors:
Marina A. Hoshiba Pimentel
;
Israel Barreto Sant'Anna
and
Marcos Didonet Del Fabro
Affiliation:
Federal University of Paraná, Brazil
Keyword(s):
Educational Resources, Terms Clustering, Ranking.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computer-Supported Education
;
e-Learning
;
e-Learning and e-Teaching
;
Enterprise Information Systems
;
Internet Portals
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Society, e-Business and e-Government
;
Software Agents and Internet Computing
;
Symbolic Systems
;
User Profiling and Recommender Systems
;
Web 2.0 and Social Networking Controls
;
Web Information Systems and Technologies
Abstract:
Open Educational Resources (OER) are important digital assets used for teaching and learning. There exists different repositories, but searching for such items is often a difficult task. On one hand, most part of the solutions implement engines with syntactic search based on term frequency metrics, or using the only item's metadata. On the other hand, the utilization of terms clustering (TC) have been used in other search and ranking contexts and they have shown to be effective. In this paper, we present an approach for searching and ranking for Open Educational Resources within a repository of objects, defining a set of tasks and an hybrid metric that integrates different ranking metrics obtained through terms clustering with the results of existing search engines (SE). We present an extensive implementation and experiments to validate our approach. The results empirically showed that our approach is effective to rank relevant OERs.