Open AccessDesign of Link Evaluation Method to Improve Reliability based on Linked Open Big Data and Natural Language Processing
Author(s) -
Yonglak Shon,
Jaeyoung Park,
Jiwon Kang,
SangWon Lee
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.33.18601
Subject(s) - computer science , linked data , ontology , reliability (semiconductor) , object (grammar) , data mining , rdf , link (geometry) , similarity (geometry) , measure (data warehouse) , information retrieval , artificial intelligence , semantic web , image (mathematics) , computer network , philosophy , power (physics) , physics , epistemology , quantum mechanics
The LOD data sets consist of RDF Triples based on the Ontology, a specification of existing facts, and by linking them to previously disclosed knowledge based on linked data principles. These structured LOD clouds form a large global data network, which provides a more accurate foundation for users to deliver the desired information. However, it is difficult to identify that, if the presence of the same object is identified differently across several LOD data sets, they are inherently identical. This is because objects with different URIs in the LOD datasets must be different and they must be closely examined for similarities in order to judge them as identical. The aim of this study is that the prosed model, RILE, evaluates similarity by comparing object values of existing specified predicates. After performing experiments with our model, we could check the improvement of the confidence level of the connection by extracting the link value.