Composição de objetos de aprendizagem multimídia através de sumarizadores automáticos de texto baseados em modelos deep learning

• Ano de defesa: 2022
• Autor(a) principal: OLIVEIRA, Leandro Massetti Ribeiro
• Orientador(a): SOARES NETO, Carlos de Salles
• Banca de defesa: SOARES NETO, Carlos de Salles , OLIVEIRA, Alexandre César Muniz de , CARVALHO, Windson Viana de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Maranhão
• Programa de Pós-Graduação: PROGRAMA DE PÓS-GRADUAÇÃO EM CIÊNCIA DA COMPUTAÇÃO/CCET
• Departamento: DEPARTAMENTO DE INFORMÁTICA/CCET
• País: Brasil
• Palavras-chave em Português: sumarização de textos; objeto de aprendizagem; deep learning; transformers;
• Palavras-chave em Inglês: text summarization,; learning object,; deep learning,; transformers.
• Área do conhecimento CNPq: Ciência da Computação
• Link de acesso: https://tedebc.ufma.br/jspui/handle/tede/4352

A Learning Object (LO) is a digital resource that can be used and reused or referenced during a process of technological support for teaching and learning. Despite being mostly multimedia, with audio, video, text and images synchronized with each other, some digital education resources have texts as one of their main elements in the teaching process, such as websites, texts, video classes, seminars, and the summarization of these texts can be a way of composing multimedia LOs. However, text summarization is a costly process in time and effort, creating the need to seek new ways to generate this content. The present work show a solution for the composition of multimedia LOs through automatic text summarizers based on Deep Learning Transformers models from two experiments: The first one composing LOs from educational texts in Portuguese using translators and text summarizers, in this experiment the results presented were positive and allow comparing the performance of summaries as generators of LO in text format; The second experiment presents an educational video summarization solution using the same Deep Learning models for subtitle summarization, the tests were performed using the EDUVSUM dataset in which it was possible to improve the results of the original article reaching 26.53% accuracy in a multi-class problem and average absolute error of 1.49 per video frame and 1.45 per video segment.