A inteligência artificial como recurso tecnológico na aplicação de tarefas para o desenvolvimento de atenção compartilhada em crianças com autismo

• Ano de defesa: 2024
• Autor(a) principal: Valentim, Nathália Assis
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; Brasil; Programa de Pós-graduação em Ciência da Computação
• Palavras-chave em Português: Inteligência Artificial; Atenção Compartilhada; Autismo; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO; Computação; Inteligência artificial; Autismo em crianças; ODS::ODS 4. Educação de qualidade - Assegurar a educação inclusiva, e equitativa e de qualidade, e promover oportunidades de aprendizagem ao longo da vida para todos.
• Link de acesso: https://repositorio.ufu.br/handle/123456789/41982; https://doi.org/10.14393/ufu.te.2024.256

People with autism may present, in addition to deficits in communication, social interaction and restricted and repetitive behavior patterns, also present deficits in joint attention, which refers to the response repertoire of following and/or directing an adult’s visual attention to objects or environmental events. Because it has a strong relationship with the learning process, joint attention deficits can compromise a person’s learning process. In this way, the use of technology can help develop skills in people with autism, such as improving joint attention, communication and social skills. In this context, the general objective of the work proposal presented here was to develop a computational approach for intervention that would allow the interaction of students with autism, aged between 4 and 5 years old, with deficits in joint attention (JA) and socio-communicative difficulties. The children used the computational approach to solve exercises developed with the aim of strengthening joint attention, where evaluation and training steps were defined, aiming to improve the learning process and contributing to the solution of open research questions. Thus, a new challenge arose to develop strategies to support the strengthening of joint attention, the deficit of which makes learning difficult, in children with autism in the preschool phase. Artificial intelligence (AI) techniques were used to model the most appropriate sequence and level of complexity of exercises for each child. AI resources were used with the intention of providing an intelligent environment to guide the child, in a dynamic and adaptive way, with the aim of promoting stimuli and adequate personalization of the process. In this way, the aim was to contribute to the advancement of the state of the art regarding the production of computational technologies for people with ASD.