Recuperação de informação de música e dados ID3: possíveis aplicações

Detalhes bibliográficos
Ano de defesa: 2015
Autor(a) principal: Ferreira, Juliano Benedito [UNESP]
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Estadual Paulista (Unesp)
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://hdl.handle.net/11449/132089
http://www.athena.biblioteca.unesp.br/exlibris/bd/cathedra/11-11-2015/000853676.pdf
Resumo: The Web Information Retrieval has become every day a chore due to increased production and availability of content. Studies addressing the Music Information Retrieval began to gain ground in the research area of information science in recent years. This work aims to approach music information retrieval methods using only the ID3 metadata as source of information. For this research we were approached music concepts in information science relating them to the formats and representations of digitally stored music. They were listed computational models of Information Retrieval and key recovery techniques as well as music information retrieval scenarios based on these techniques, and as a source of information only the ID3 metadata. In the first scenario, the user is not identified for access and the system does not record the number of times that a particular item was accessed, the results presented only give based on ID3 metadata. In the second proposed scenario, the user remains unidentified, but the system will count the number of hits a particular document, allowing the user to select documents based on their amount of hits. In the third scenario, based on user identification, it would be possible to establish a search profile, applying information retrieval techniques listed above. The proposed scenarios showed that you can retrieve music information only using the ID3 metadata applying information retrieval techniques such as filtering, grouping, relevance feedback and recommendation systems.