Publicação

Tuning metadata for better movie content-based recommendation systems

Ver documento

Detalhes bibliográficos
Resumo:The increasing number of television channels, on-demand services and online content, is expected to contribute to a better quality of experience for a costumer of such a service. However, the lack of efficient methods for finding the right content, adapted to personal interests, may lead to a progressive loss of clients. In such a scenario, recommendation systems are seen as a tool that can fill this gap and contribute to the loyalty of users. Multimedia content, namely films and television programmes are usually described using a set of metadata elements that include the title, a genre, the date of production, and the list of directors and actors. This paper provides a deep study on how the use of different metadata elements can contribute to increase the quality of the recommendations suggested. The analysis is conducted using Netflix and Movielens datasets and aspects such as the granularity of the descriptions, the accuracy metric used and the sparsity of the data are taken into account. Comparisons with collaborative approaches are also presented.
Autores principais:Márcio Micael Soares
Outros Autores:Paula Viana
Ano:2015
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:INESC TEC
Idioma:inglês
Origem:INESC TEC
_version_ 1868329918838865920
author Márcio Micael Soares
author2 Paula Viana
author2_role author
author_facet Márcio Micael Soares
Paula Viana
author_role author
country_str PT
creators_json_txt [{\"Person.name\":\"Márcio Micael Soares\"},{\"Person.name\":\"Paula Viana\"}]
datacite.creators.creator.creatorName.fl_str_mv Márcio Micael Soares
Paula Viana
datacite.date.Accepted.fl_str_mv 2015-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2017-12-14T14:17:54Z
datacite.date.embargoed.fl_str_mv 2017-12-14T14:17:54Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.titles.title.fl_str_mv Tuning metadata for better movie content-based recommendation systems
dc.creator.none.fl_str_mv Márcio Micael Soares
Paula Viana
dc.date.Accepted.fl_str_mv 2015-01-01T00:00:00Z
dc.date.available.fl_str_mv 2017-12-14T14:17:54Z
dc.date.embargoed.fl_str_mv 2017-12-14T14:17:54Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://repositorio.inesctec.pt/handle/123456789/4089
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.title.fl_str_mv Tuning metadata for better movie content-based recommendation systems
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description The increasing number of television channels, on-demand services and online content, is expected to contribute to a better quality of experience for a costumer of such a service. However, the lack of efficient methods for finding the right content, adapted to personal interests, may lead to a progressive loss of clients. In such a scenario, recommendation systems are seen as a tool that can fill this gap and contribute to the loyalty of users. Multimedia content, namely films and television programmes are usually described using a set of metadata elements that include the title, a genre, the date of production, and the list of directors and actors. This paper provides a deep study on how the use of different metadata elements can contribute to increase the quality of the recommendations suggested. The analysis is conducted using Netflix and Movielens datasets and aspects such as the granularity of the descriptions, the accuracy metric used and the sparsity of the data are taken into account. Comparisons with collaborative approaches are also presented.
dirty 0
eu_rights_str_mv openAccess
format article
id inesctec_8e7b61aa7cb95763f08ebfdbac2c19e8
identifier.url.fl_str_mv http://repositorio.inesctec.pt/handle/123456789/4089
instacron_str inesctec
institution INESC TEC
instname_str INESC TEC
language eng
network_acronym_str inesctec
network_name_str INESC TEC
oai_identifier_str oai:repositorio.inesctec.pt:123456789/4089
organization_str_mv urn:organizationAcronym:inesctec
person_str_mv Márcio Micael Soares
Paula Viana
publishDate 2015
reponame_str INESC TEC
repository_id_str urn:repositoryAcronym:inesctec
service_str_mv urn:repositoryAcronym:inesctec
spelling engThe increasing number of television channels, on-demand services and online content, is expected to contribute to a better quality of experience for a costumer of such a service. However, the lack of efficient methods for finding the right content, adapted to personal interests, may lead to a progressive loss of clients. In such a scenario, recommendation systems are seen as a tool that can fill this gap and contribute to the loyalty of users. Multimedia content, namely films and television programmes are usually described using a set of metadata elements that include the title, a genre, the date of production, and the list of directors and actors. This paper provides a deep study on how the use of different metadata elements can contribute to increase the quality of the recommendations suggested. The analysis is conducted using Netflix and Movielens datasets and aspects such as the granularity of the descriptions, the accuracy metric used and the sparsity of the data are taken into account. Comparisons with collaborative approaches are also presented.application/pdfengengTuning metadata for better movie content-based recommendation systemsMárcio Micael SoaresPaula VianaURLhttp://repositorio.inesctec.pt/handle/123456789/4089DOIhttp://dx.doi.org/10.1007/s11042-014-1950-12017-12-14T14:17:54Z2015-01-01T00:00:00Z2015http://purl.org/coar/access_right/c_abf2open access1061836 byteshttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorio.inesctec.pt/bitstreams/27fa951f-a02c-46b8-8b8e-b2da127b21d0/downloadliteraturehttp://purl.org/coar/resource_type/c_6501journal article
spellingShingle Tuning metadata for better movie content-based recommendation systems
Márcio Micael Soares
status SINGLETON
title Tuning metadata for better movie content-based recommendation systems
title_full Tuning metadata for better movie content-based recommendation systems
title_fullStr Tuning metadata for better movie content-based recommendation systems
title_full_unstemmed Tuning metadata for better movie content-based recommendation systems
title_short Tuning metadata for better movie content-based recommendation systems
title_sort Tuning metadata for better movie content-based recommendation systems
url http://repositorio.inesctec.pt/handle/123456789/4089
visible 1