Use of ontology in the retrieval of information in digital collections of newspapers

Introduction: It aims at modeling an ontology of the soccer field for the treatment of diachronic and synchronic variations of the language; Objective: To support the retrieval of information in digital collections of newspapers. Methodology: This is an applied research, using as basis a digital jou...

Descripción completa

Detalles Bibliográficos
Autores: Santos, Luana Carla de Moura dos, Bräscher, Marisa
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:Brasil
Institución:Universidade Estadual de Londrina (UEL)
Repositorio:Informação & Informação
Idioma:portugués
OAI Identifier:oai:ojs.pkp.sfu.ca:article/28782
Acceso en línea:https://ojs.uel.br/revistas/uel/index.php/informacao/article/view/28782
Access Level:acceso abierto
Palabra clave:Information Retrieval
Digital Newspaper Collection
Domain Ontology
Soccer
Recuperación de la Información
Colección Digital del Periódico
Ontología de Dominio
Fútbol
Recuperação da Informação
Acervo Digital de Jornal
Ontologia de Domínio
Futebol
Descripción
Sumario:Introduction: It aims at modeling an ontology of the soccer field for the treatment of diachronic and synchronic variations of the language; Objective: To support the retrieval of information in digital collections of newspapers. Methodology: This is an applied research, using as basis a digital journal collection. It uses the methodology OntoForInfoScience, de Mendonça (2015) to develop the ontology of the soccer field. Information collection was carried out on domain reference materials and newspaper news. Chronologically, the established cut covers terminology used between 1900 to 2015, a period that contemplates the existence of football clubs in Brazil. The ontology was formalized in logical language with the help of the editor Protegé. As a way of evaluating the developed ontology, competence issues were elaborated that were executed in SPARQL language. To verify the use of the ontology in environments composed by printed and digital newspapers, demonstrative searches were carried out in a real collection. Results: The analysis of the results showed that without the use of the ontology in the digital collections of newspapers, the information retrieval is exhaustive and retrieves documents that are not relevant due to the absence of relationships between the terms that form the domain. Conclusion: With the inclusion of the ontology, the search for information can dispense with both the user's literacy, because with the relationships formed, it is not necessary to perform numerous searches to retrieve equivalent concepts and expressions.