Recommender TV: suporte ao desenvolvimento de aplicações de recomendação para o Sistema Brasileiro de TV Digital

• Ano de defesa: 2010
• Autor(a) principal: Ávila, Paulo Muniz de
• Orientador(a): Zorzo, Sérgio Donizetti
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• País: BR
• Palavras-chave em Português: Métodos especiais de computação; Televisão digital; Personalização; Middleware; Ginga
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/429

Digital television will allow the transmission of new services, with a significant increase in the amount of information available to users compared to traditional analog system. Given that growth of possible applications, recommendation systems have emerged as useful tools to help viewers cope with this overload of information, allowing identify their needs and preferences. For this reason, this work presents a solution to support the development of recommender systems, by adding a new module in the middleware Ginga entitled Recommender TV. Thus, it was implemented an abstraction layer that allows developers of applications for interactive digital television, specifically for developers of recommender systems, be concerned with the interface and navigability of their systems, leaving questions of low-level module Recommender TV manage. Issues regarding the low level processing the new module presented in this work allows the implementation of different recommender systems, quickly and efficiently. The use of the results provided by such systems will assist us to better understand the implementation of interactive digital television.