Aplicação de Learning Analytics para Modelagem do Aluno de acordo com a Taxonomia de Bloom Revisada

• Autor(a) principal: Carneiro, Janalívia do Nascimento
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da UFPB
• Texto Completo: https://repositorio.ufpb.br/jspui/handle/123456789/14483
• topic: Educação Adaptativa; Sistemas de Aprendizagem Adaptativos; Modelos do Aluno; Learning Analytics; Taxonomia de Bloom Revisada; Adaptive Education; Adaptive Learning Systems; Student Models; Learning Analytics; Revised Bloom Taxonomy; Educação a distância - Ambientes virtuais de aprendizagem; Educação adaptativa; Taxonomia de bloom revisada; Learning Analytics; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO

Virtual Learning Environments (VLEs) are educational resources resulting from technological development which can be an alternative to maximize the capacity of virtual online education. However, the vast majority of learning environments that are available to students are used in a passive way, mainly to transmit multimedia documents (videos, audios, texts, images, etc.) and provide ways to evaluate students through questionnaires and activity submissions, not offering a customized instructional material for the different types of student. An example of such systems is the Modular Object Oriented Dynamic Learning Environment (Moodle). One possible way to address this problem is through the usage of Adaptive Learning System (ALS). ALS systems take into account the information accumulated in individual learners’ models in order to behave differently for different kinds of students. Student modeling plays a crucial role in an ALS because it provides information about the student’s learning profile, which allows the systems to be highly individualized. The adaptation of the system can happen in different ways and levels, offering personalized teaching. This research proposes an adaptive model that takes into account the cognitive profiles of the learners. The proposed model uses a combination of Learning Analytics (LA), which is a technique for extracting academic data in order to provide visualization about the learning process, to provide a representation of the student’s learning profile, according to the Revised Bloom Taxonomy (RBT), which is a framework for classifying the different levels of human cognition of thought, learning and understanding. Through the application of LA, the learner’s learning trajectory will be evaluated dynamically using the indicators of the RBT, which later on can be used as basis for adaptation of the teaching level offered to the different learning level of the students.