Uma linguagem para modelagem do vocabulário de pranchas de comunicação alternativa

• Ano de defesa: 2014
• Autor(a) principal: Franco, Natália de Melo
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Alagoas; Brasil; Programa de Pós-Graduação em Modelagem Computacional de Conhecimento; UFAL
• Palavras-chave em Português: Tecnologia assistiva; Distúrbios da fala; Assistive technology; Speech disorders; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: http://www.repositorio.ufal.br/handle/riufal/1760

Every year, the world’s population increases by, approximately, one hundred thousand people whose disabilities severely limit their communication process. The cause of these disabilities can be physical, psychological or cognitive. These people may have a limited capacity of communication, resulting in accessibility problems in their daily lives and, for these cases, Assistive Technologies based on Alternative Communication Boards (ACB) can be used to aid communication. It is important that the contents of ACB reflect the needs and preferences of each patient and that this content can be edited or evolved by professionals and caregivers. Considering the need to personalize the ACB for each patient, the existing solutions have two important limitations: 1) the personalization of content, when is possible, is made by software developers, or through Graphical User Interface (GUI), by filling predefined fields; and 2) the possibility of generating low-cohesive messages (e.g., "drink a chocolate cookie"). A way to improve this customization is using a Domain-Specific Modeling Language (DSML). Since this allows a graphical representation of domain concepts, it improves learning and makes the use easier. This study supports the hypothesis that a modeling language has the required expressiveness to allow personalization of the ACB in several domains. In this context, this work aims to create a new paradigm for the ACB content’s personalization in order to limit the occurrence of low-cohesive messages. The specified DSML were evaluated by professionals in terms of feasibility and expressiveness.