Fabiano Azevedo Dorça

Dr. Fabiano Azevedo Dorça

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2015 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
Studies attest that learning is facilitated if teaching strategies are in accordance with students learning styles, making learning process more effective and considerably improving students performances. In this context, one major research point – and a challenge – is to efficiently discover students’ learning styles. But, the test and validation of new approaches in this field requires substantial amounts of financial, human resources (tutors and students) and time. In this way, the use of simulated students for test and validation of new approaches in this field is very important. Therefore, this work depicts the implementation and use of simulation for empirical evaluation of three different strategies for automatic learning styles modelling. It was necessary to compare the efficiency of the strategies, in order to choose the best one. Therefore, it was needed a practical mechanism to evaluate and compare them, preferably without the engagement of human resources. Then, the main goal of using simulation in this work is to compare strategies’ efficiency and to discover the most promising one. The research was empirical, and has led to considerable enhancements on an intelligent component for automatic modelling of learning and teaching styles, which has been tested, adjusted and improved in a reasonable time and with low cost. The best strategy was clearly found, as depicted by experiments and results presented in this paper.

1 November 2016
Verified
Conference Paper
Closed access
HFHiran Nonato M. Ferreira
Hiran Nonato M. Ferreira
TBTaffarel Brant-Ribeiro
Taffarel Brant-Ribeiro
RARafael D. Araujo
Rafael D. Araujo
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
RCRenan G. Cattelan
Renan G. Cattelan
Dynamic adaptation of educational content has been an important research topic. Therefore, in order for it to run effectively, student models that properly describe and monitor the cognitive state of students are needed. In this sense, this paper presents a hybrid student model approach that combines ontologies and Bayesian Networks to identify the knowledge of each student based on their characteristics and behavior while using an Adaptive Educational System. Experiments were performed with real student participants in a higher education course using an experimental prototype developed to verify the viability of the approach, which showed satisfactory results.

28 November 2025 in Computer Applications in Engineering Education
Verified
Journal Article
Open access
GLGeycy Dyany O. Lima
Geycy Dyany O. Lima
JCJuliete A. R. Costa
Juliete A. R. Costa
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
RARafael D. Araújo
Rafael D. Araújo
This study reports on the design, implementation, and evaluation of an AI‐Supported Pedagogical Architecture (PA) aimed at fostering Self‐Regulated Learning (SRL) within a Virtual Learning Environment (VLE). The architecture was integrated into the Moodle platform and applied in an introductory Python course. It incorporates technological tools such as Completion Progress, Analytics Graphs, Athena, and the Time Tracker SRL plugin to deliver real‐time feedback, facilitate progress monitoring, and support learners in goal setting, planning, and reflection–key dimensions of SRL. Through Educational Data Mining techniques, the study identifies distinct learner profiles based on interaction logs, revealing a significant correlation between SRL strategies and academic achievement. Additionally, qualitative data from focus groups underscore the architecture's effectiveness in enhancing metacognitive awareness, student engagement, and overall satisfaction, demonstrating its potential to support the development of learner autonomy in online education.

16 February 2020 in Revista Brasileira de Informática na Educação
Verified
Journal Article
Open access
PDF file
RARafael D. Araújo
Rafael D. Araújo
TBTaffarel Brant-Ribeiro
Taffarel Brant-Ribeiro
HFHiran N. M. Ferreira
Hiran N. M. Ferreira
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
RCRenan G. Cattelan
Renan G. Cattelan
The fact that people behave and learn in a different pace requires individual differences to be properly considered in the teaching/learning process. Among several cognitive theories that could be used for this purpose, a promising one is to explore the use of students' learning styles (LSs), with several research studies indicating that their use has positive impacts on learning outcomes. At the same time, Ubiquitous Learning Environments (ULEs) have the potential to make the multimedia authoring of Learning Objects (LOs) an automated process, resulting on even larger educational content repositories and increasing the need for more adequate presentation strategies to students. This article presents an approach for creating and personalizing LOs through a probabilistic proposal of the Felder and Silverman Learning Styles Model. A prototype of the proposed model was integrated into a ubiquitous educational platform and experimented in real settings. Results indicate the existence of correlations between different types of interactions carried out by students and their respective LSs.

6 January 2023 in Revista Brasileira de Informática na Educação
Verified
Journal Article
Open access
PDF file
CJCleon Xavier Pereira Júnior
Cleon Xavier Pereira Júnior
RARafael Dias Araújo
Rafael Dias Araújo
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
A área de Sistemas Adaptativos e Inteligentes para a Educação está em constante evolução e visa criar ambientes de aprendizagem personalizados através da aplicação de tecnologias recentes, incluindo técnicas de Inteligência Artificial, combinadas com teorias pedagógicas. Este trabalho visa contribuir para a área de IA aplicada à educação, utilizando uma abordagem que combina tecnologias de Web Semântica e um algoritmo bioinspirado para realização recomendação personalizada de objetos de aprendizagem por meio de filtragem baseada em conteúdo. Em contraste com outras abordagens, este estudo combina repositórios de Ambientes Virtuais de Aprendizagem (AVA) com materiais disponíveis na Web (YouTube e Wikipedia) para fornecer recursos educacionais em formatos diversos sobre um determinado tópico. Os materiais da Web são recuperados e estruturados como objetos de aprendizagem. A abordagem foi testada no Classroom eXperience (CX) e também foi criado um recurso de extensão para o Moodle. Experimentos foram realizados para testar a abordagem. Um dos experimentos objetivou analisar a opinião dos estudantes em relação à recomendação personalizada. Os estudantes avaliaram positivamente a recomendação que considerou o nível de conhecimento e ofereceu materiais adicionais sobre o tema. Outro experimento considerou três processos de recomendação diferentes para observar as preferências dos estudantes. As recomendações consideraram o uso e não uso de estilos de aprendizagem no processo. A média geral da avaliação foi relativamente melhor desconsiderando o uso dos estilos de aprendizagem, mas não houve significância estatística.

28 October 2018
Verified
Conference Paper
Open access
PDF file
CJClarivando Belizário Júnior
Clarivando Belizário Júnior
FDFabiano Azevedo Dorça
Fabiano Azevedo Dorça
O e-learning é um modelo de ensino eletrônico que pode ser adaptado aos estilos de aprendizagem de cada estudante. A carência de objetos de aprendizagem (OAs) que possam ser recomendados aos alunos é um problema pendente. O segundo desafio é a própria recomendação desses OAs. Para solucioná-los, implementa-se uma abordagem que utiliza conteúdo da Wikipédia para a criação de novos recursos educacionais e uma ontologia para a modelagem de estudantes e OAs. O problema da recomendação de OAs é formalizado, então apresenta-se um algoritmo genético para solucionálo. Os testes realizados em um protótipo garantem a viabilidade dessa abordagem na solução desses problemas.