dc.creatorFortes, Arthur
dc.creatorManzato, Marcelo Garcia
dc.date.accessioned2015-03-23T14:32:00Z
dc.date.accessioned2018-07-04T17:03:33Z
dc.date.available2015-03-23T14:32:00Z
dc.date.available2018-07-04T17:03:33Z
dc.date.created2015-03-23T14:32:00Z
dc.date.issued2014-11
dc.identifierBrazilian Symposium on Multimedia and the Web, 20th, 2014, João Pessoa.
dc.identifier9781450332309
dc.identifierhttp://www.producao.usp.br/handle/BDPI/48609
dc.identifierhttp://dx.doi.org/10.1145/2664551.2664556
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1644089
dc.description.abstractIn this paper, we propose a technique that uses multimodal interactions of users to generate a more accurate list of recommendations optimized for the user . Our approach is a response to the actual scenario on the Web which allows users to interact with the content in different ways, and thus, more information about his preferences can be obtained to improve recommendation. The proposal consists of an ensemble learning technique that combines rankings generated by unimodal recommenders based on particular interaction types. By using a combination of different types of feedback from users, we are able to provide better recommendations, as shown by our experimental evaluation.
dc.languageeng
dc.publisherUniversidade Federal da Paraíba - UFPB
dc.publisherNúcleo de Pesquisa e Extensão em Aplicações de Vídeo Digital - LAViD
dc.publisherSociedade Brasileira de Computação - SBC
dc.publisherJoão Pessoa
dc.relationBrazilian Symposium on Multimedia and the Web, 20th
dc.rightsCopyright ACM
dc.rightsclosedAccess
dc.subjectAlgorithms
dc.subjectRecommender Systems
dc.subjectEnsemble Learning
dc.subjectMutimodals Interecations
dc.titleEnsemble learning in recommender systems: combining multiple user interactions for ranking personalization
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución