Adriano Ferreti Borgatto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Adriano Ferreti Borgatto has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
- Christiane Gresse von Wangenheim
Universidade Federal de Santa Catarina (UFSC)
21 shared publications - Jean Carlo Rossa Hauck
UFSC
13 shared publications - Marcelo Fernando Rauber
Federal University of Santa Catarina and Federal Institute Catarinense, Brazil
9 shared publications - Ramon Mayor Martins
Instituto Federal de Santa Catarina
8 shared publications - Adriana Coutinho de Azevedo Guimarães
Universidade do Estado de Santa Catarina image/svg+xml
7 shared publications - Giani Petri
Universidade Federal de Santa Maria (UFSM)
5 shared publications
Latest Publications
Modified Atkins diet therapy in adult drug‐resistant epilepsy: Quality of life and mental health outcomes
Objective: This study aims to assess the effect of ketogenic diet therapy on seizure frequency, quality of life, and mental health symptoms in adults with drug‐resistant epilepsy (DRE). Methods: We conducted a longitudinal, quantitative, prospective, and single‐center cohort study. Patients were recruited from a tertiary health care center in Brazil. The modified Atkins diet was prescribed to adult (≥18 years old) patients with DRE. Patients were accompanied closely by a specialized team of doctors and nutritionists, with a nutritionist available 24/7. Blood ketone levels were measured using a β‐hydroxybutyrate meter and corresponding test strips. Patients were instructed to record all events in a seizure diary and completed questionnaires (Quality of Life in Epilepsy Inventory 31 [QOLIE‐31], Hospital Anxiety and Depression Scale [HADS], and Adult Self‐Report Scale [ASRS]) during the follow‐up period to evaluate mental health and quality of life. Joint multiple imputation was used to address missing data, and statistical analysis was performed with linear mixed models. Results: A total of 17 patients were included, of whom nine were followed up for a total of 12 months and six for 6 months, and two completed 3 months of diet. Ten of the patients presented with focal to bilateral tonic–clonic seizures, and only one had generalized epilepsy. At 12 months of diet, QOLIE‐31 scores increased significantly (+17.21, p = .043, 95% confidence interval [CI] = .56–33.86), and anxiety scores (HADS‐A) also showed a significant improvement (−4.38, p = .01, 95% CI = −7.63 to −1.07). No significant changes were observed in seizure frequency or ASRS. Significance: In this single‐arm prospective cohort study, modified Atkins diet therapy was associated with improved quality of life and reduced anxiety symptoms in adults with DRE, independent of major changes in seizure frequency.
Modified Atkins diet therapy in adult drug‐resistant epilepsy: Quality of life and mental health outcomes
Objective: This study aims to assess the effect of ketogenic diet therapy on seizure frequency, quality of life, and mental health symptoms in adults with drug‐resistant epilepsy (DRE). Methods: We conducted a longitudinal, quantitative, prospective, and single‐center cohort study. Patients were recruited from a tertiary health care center in Brazil. The modified Atkins diet was prescribed to adult (≥18 years old) patients with DRE. Patients were accompanied closely by a specialized team of doctors and nutritionists, with a nutritionist available 24/7. Blood ketone levels were measured using a β‐hydroxybutyrate meter and corresponding test strips. Patients were instructed to record all events in a seizure diary and completed questionnaires (Quality of Life in Epilepsy Inventory 31 [QOLIE‐31], Hospital Anxiety and Depression Scale [HADS], and Adult Self‐Report Scale [ASRS]) during the follow‐up period to evaluate mental health and quality of life. Joint multiple imputation was used to address missing data, and statistical analysis was performed with linear mixed models. Results: A total of 17 patients were included, of whom nine were followed up for a total of 12 months and six for 6 months, and two completed 3 months of diet. Ten of the patients presented with focal to bilateral tonic–clonic seizures, and only one had generalized epilepsy. At 12 months of diet, QOLIE‐31 scores increased significantly (+17.21, p = .043, 95% confidence interval [CI] = .56–33.86), and anxiety scores (HADS‐A) also showed a significant improvement (−4.38, p = .01, 95% CI = −7.63 to −1.07). No significant changes were observed in seizure frequency or ASRS. Significance: In this single‐arm prospective cohort study, modified Atkins diet therapy was associated with improved quality of life and reduced anxiety symptoms in adults with DRE, independent of major changes in seizure frequency.
- Open Access
- 27 August 2025
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 33, 943-971
Using MEEGA/MEEGA+ for the Evaluation of Educational Games: A Retrospective
Educational games are assumed to be an effective and efficient instructional strategy. However, it is essential to systematically evaluate such games in order to obtain sound evidence of their impact. An alternative is the MEEGA/MEEGA+ model, providing support to evaluate games in terms of motivation, user experience, and learning based on the reaction of the students. Since its first publication in 2011 originally focusing on games for teaching Software Engineering it has been adopted for a wide range of games and knowledge domains. Thus, the objective of this article is to present a systematic mapping on the application of the MEEGA/MEEGA+ model identifying 166 relevant articles, and describing 170 studies on the evaluation of 178 serious games. Findings show that the model is mostly used as-is in case studies as an easy way to evaluate games in the classroom, with fewer studies simplifying the data collection instrument and/or completing the data collection with other measurement instruments. This shows that especially the improved version MEEGA+ is a well-accepted model for the evaluation of serious games in order to assist game creators and instructors to improve such games as well as to support decisions on their application within instructional units.
- 27 August 2025
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 33, 943-971
Open AccessUsing MEEGA/MEEGA+ for the Evaluation of Educational Games: A Retrospective
Educational games are assumed to be an effective and efficient instructional strategy. However, it is essential to systematically evaluate such games in order to obtain sound evidence of their impact. An alternative is the MEEGA/MEEGA+ model, providing support to evaluate games in terms of motivation, user experience, and learning based on the reaction of the students. Since its first publication in 2011 originally focusing on games for teaching Software Engineering it has been adopted for a wide range of games and knowledge domains. Thus, the objective of this article is to present a systematic mapping on the application of the MEEGA/MEEGA+ model identifying 166 relevant articles, and describing 170 studies on the evaluation of 178 serious games. Findings show that the model is mostly used as-is in case studies as an easy way to evaluate games in the classroom, with fewer studies simplifying the data collection instrument and/or completing the data collection with other measurement instruments. This shows that especially the improved version MEEGA+ is a well-accepted model for the evaluation of serious games in order to assist game creators and instructors to improve such games as well as to support decisions on their application within instructional units.
- Open Access
- 22 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing Education
Scale for Assessing the Learning of Machine Learning for Image Classification in Middle and High School Using the “ML for All” Course
The current insertion of Machine Learning (ML) in our everyday life demonstrates the importance of introducing the teaching of a basic understanding of ML already in school. Accompanying this trend arises the need to assess the students’ learning of ML, yet so far only a few assessment models have been proposed, most of them rather simple, based on quizzes or self-assessments. In this context, we previously developed and evaluated a model for the performance-based assessment of the student’s learning of ML for image classification based on the ML artifacts created by the students as a learning outcome as part of the “ML for All” course, indicating good reliability (coefficient Omega = 0.834) and validity. Evolving this assessment model, we present in this article a scale associated with the level of student learning and a descriptive interpretation of student performance using Item Response Theory (IRT) based on data collected from 240 students. The results of this research can support the learning of ML by providing feedback to students and supporting teachers.
- 22 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing Education
Open AccessScale for Assessing the Learning of Machine Learning for Image Classification in Middle and High School Using the “ML for All” Course
The current insertion of Machine Learning (ML) in our everyday life demonstrates the importance of introducing the teaching of a basic understanding of ML already in school. Accompanying this trend arises the need to assess the students’ learning of ML, yet so far only a few assessment models have been proposed, most of them rather simple, based on quizzes or self-assessments. In this context, we previously developed and evaluated a model for the performance-based assessment of the student’s learning of ML for image classification based on the ML artifacts created by the students as a learning outcome as part of the “ML for All” course, indicating good reliability (coefficient Omega = 0.834) and validity. Evolving this assessment model, we present in this article a scale associated with the level of student learning and a descriptive interpretation of student performance using Item Response Theory (IRT) based on data collected from 240 students. The results of this research can support the learning of ML by providing feedback to students and supporting teachers.
- Open Access
- 7 July 2025
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 33, 1596-1622
Comparing the Perceptions of Middle and High School Students from Different Socioeconomic Status Backgrounds on Learning Machine Learning
Machine Learning (ML) is increasingly integral to modern life, requiring its introduction to young individuals across all socioeconomic status (SES) backgrounds. Various initiatives are emerging for the integration of ML into the education of young students including the development of curricula, courses and activities. And although first applications indicate positive findings with regard to the students’ learning, there still is a lack of research on the effect of such teaching efforts across students from different SES backgrounds. Therefore, this study investigates the impact of different SES backgrounds on the students' understanding and application of ML basic concepts through the application of the ML4ALL! course to 266 middle and high school students from different SES backgrounds. The findings reveal significant differences in students' understanding and explanation of ML concepts, indicating that this may be affected by their SES background. However, students' perceived ability to apply ML concepts and the perceived difficulty in learning ML were consistent across all groups. The results indicate that although the SES background may influence students' learning, it does not necessarily limit their perceived ability to engage with AI/ML concepts. The insights from this study may contribute to a better understanding of the perceptions of students from a low SES background regarding AI/ML learning and can assist in facilitating the development of inclusive, effective, and enjoyable educational approaches.
- 7 July 2025
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 33, 1596-1622
Open AccessComparing the Perceptions of Middle and High School Students from Different Socioeconomic Status Backgrounds on Learning Machine Learning
Machine Learning (ML) is increasingly integral to modern life, requiring its introduction to young individuals across all socioeconomic status (SES) backgrounds. Various initiatives are emerging for the integration of ML into the education of young students including the development of curricula, courses and activities. And although first applications indicate positive findings with regard to the students’ learning, there still is a lack of research on the effect of such teaching efforts across students from different SES backgrounds. Therefore, this study investigates the impact of different SES backgrounds on the students' understanding and application of ML basic concepts through the application of the ML4ALL! course to 266 middle and high school students from different SES backgrounds. The findings reveal significant differences in students' understanding and explanation of ML concepts, indicating that this may be affected by their SES background. However, students' perceived ability to apply ML concepts and the perceived difficulty in learning ML were consistent across all groups. The results indicate that although the SES background may influence students' learning, it does not necessarily limit their perceived ability to engage with AI/ML concepts. The insights from this study may contribute to a better understanding of the perceptions of students from a low SES background regarding AI/ML learning and can assist in facilitating the development of inclusive, effective, and enjoyable educational approaches.
- Open Access
- 4 November 2024
- Published by Sociedade Brasileira de Computação
- p. 15-29
Proposta de Escala para Avaliação da Aprendizagem de Machine Learning em nível Create na Educação Básica
Há uma tendência de incluir o ensino de Machine Learning (ML) já na Educação Básica, ensinando os alunos a criar suas próprias soluções inteligentes. Nesse contexto, também é importante avaliar o aprendizado de ML e do processo de Design Thinking em nível Create. Evoluindo um modelo de avaliação, este artigo tem como objetivo propor uma escala com sua interpretação pedagógica utilizando a Teoria de Resposta ao Item (TRI). Os resultados fornecem uma primeira indicação da adequação do modelo de avaliação em relação à consistência interna e parâmetros de calibração da TRI muito próximos aos aceitáveis. Esperamos que a definição da escala possa apoiar o aprendizado da criação de soluções de ML fornecendo feedback aos alunos e professores.
- 4 November 2024
- Published by Sociedade Brasileira de Computação
- p. 15-29
Open AccessProposta de Escala para Avaliação da Aprendizagem de Machine Learning em nível Create na Educação Básica
Há uma tendência de incluir o ensino de Machine Learning (ML) já na Educação Básica, ensinando os alunos a criar suas próprias soluções inteligentes. Nesse contexto, também é importante avaliar o aprendizado de ML e do processo de Design Thinking em nível Create. Evoluindo um modelo de avaliação, este artigo tem como objetivo propor uma escala com sua interpretação pedagógica utilizando a Teoria de Resposta ao Item (TRI). Os resultados fornecem uma primeira indicação da adequação do modelo de avaliação em relação à consistência interna e parâmetros de calibração da TRI muito próximos aos aceitáveis. Esperamos que a definição da escala possa apoiar o aprendizado da criação de soluções de ML fornecendo feedback aos alunos e professores.
- Open Access
- 30 September 2024
- Published by Sociedade Brasileira de Computação
- p. 80-91
How do Agile Organizations Manage Risks: An Analysis of the State of Practice in Brazil
The use of agile methods tends to keep risks under control in software projects, due to their inherent characteristics of small increments, work visibility and expectation management. Thus, explicit risk management in agile projects has often been neglected, as the use of agile methods, with a focus on rapid value delivery, tends to lead to implicit risk management. However, software projects that use agile methods also can fail and implicit risk management may often not be sufficient for certain contexts. This has sparked research interest in the possible need for explicit risk management in software organizations that use agile methods. Motivated by the lack of information about risk management in agile software development contexts, in this work a comprehensive survey is carried out to understand how software development organizations that use agile methods are managing risk. We conducted an online survey with a statistically significant sample of 273 agile professionals in Brazil. Our findings indicate that although most organizations engage in some form of explicit risk management, a significant proportion consider agile methods insufficient for comprehensive risk mitigation. We also observed a set of 15 explicit risk management practices in agile contexts, with some agile ceremonies, notably daily and sprint planning meetings, emerging as conducive to the integration of explicit risk management practices. We also verified a statistically relevant association between these agile ceremonies and risk management processes.
- 30 September 2024
- Published by Sociedade Brasileira de Computação
- p. 80-91
Open AccessHow do Agile Organizations Manage Risks: An Analysis of the State of Practice in Brazil
The use of agile methods tends to keep risks under control in software projects, due to their inherent characteristics of small increments, work visibility and expectation management. Thus, explicit risk management in agile projects has often been neglected, as the use of agile methods, with a focus on rapid value delivery, tends to lead to implicit risk management. However, software projects that use agile methods also can fail and implicit risk management may often not be sufficient for certain contexts. This has sparked research interest in the possible need for explicit risk management in software organizations that use agile methods. Motivated by the lack of information about risk management in agile software development contexts, in this work a comprehensive survey is carried out to understand how software development organizations that use agile methods are managing risk. We conducted an online survey with a statistically significant sample of 273 agile professionals in Brazil. Our findings indicate that although most organizations engage in some form of explicit risk management, a significant proportion consider agile methods insufficient for comprehensive risk mitigation. We also observed a set of 15 explicit risk management practices in agile contexts, with some agile ceremonies, notably daily and sprint planning meetings, emerging as conducive to the integration of explicit risk management practices. We also verified a statistically relevant association between these agile ceremonies and risk management processes.
- Open Access
- 27 September 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing Education
- Vol. 24 (3) , 1-31
Exploring the Relationship between Learning of Machine Learning Concepts and Socioeconomic Status Background among Middle and High School Students: A Comparative Analysis
As Machine Learning (ML) becomes increasingly integrated into our daily lives, it is essential to teach ML to young people from an early age including also students from a low socioeconomic status (SES) background. Yet, despite emerging initiatives for ML instruction in K-12, there is limited information available on the learning of students from a low SES background. To address this gap, our study conducted an analysis of comparing the students’ performance assessment scores of ML concepts as a result of the ML4ALL! course among 266 middle and high school students from different socioeconomic backgrounds. The results demonstrated an understanding of ML concepts among students from all SES backgrounds. Although some differences were observed regarding specific parts of the ML development process, these were not substantial enough to identify SES as a determining factor affecting the performance assessment score. Also, when considering the background together with other demographic factors such as sex assigned at birth or educational stage, no significant difference of the students’ performance assessment scores was observed. These findings provide a first indication that a low SES background must not be a barrier to ML competencies and that effective and inclusive ML teaching strategies can ensure equitable access to ML education across diverse socioeconomic backgrounds.
- 27 September 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing Education
- Vol. 24 (3) , 1-31
Open AccessExploring the Relationship between Learning of Machine Learning Concepts and Socioeconomic Status Background among Middle and High School Students: A Comparative Analysis
As Machine Learning (ML) becomes increasingly integrated into our daily lives, it is essential to teach ML to young people from an early age including also students from a low socioeconomic status (SES) background. Yet, despite emerging initiatives for ML instruction in K-12, there is limited information available on the learning of students from a low SES background. To address this gap, our study conducted an analysis of comparing the students’ performance assessment scores of ML concepts as a result of the ML4ALL! course among 266 middle and high school students from different socioeconomic backgrounds. The results demonstrated an understanding of ML concepts among students from all SES backgrounds. Although some differences were observed regarding specific parts of the ML development process, these were not substantial enough to identify SES as a determining factor affecting the performance assessment score. Also, when considering the background together with other demographic factors such as sex assigned at birth or educational stage, no significant difference of the students’ performance assessment scores was observed. These findings provide a first indication that a low SES background must not be a barrier to ML competencies and that effective and inclusive ML teaching strategies can ensure equitable access to ML education across diverse socioeconomic backgrounds.
- Open Access
- 8 March 2024
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 30 (1) , 102-115
A Deep Learning Model for the Assessment of the Visual Aesthetics of Mobile User Interfaces
Visual aesthetics is one of the first aspects that users experience when looking at graphical user interfaces (GUIs), contributing to the perceived usability and credibility of a software system. It can also be an essential success factor in contexts where graphical elements play an important role in attracting users, such as choosing a mobile app from an app store. Therefore, visual aesthetics assessments are crucial in interface design, but traditional methods, involving target user representatives assessing each GUI individually, are costly and time-consuming. In this context, machine learning models have been demonstrated to be promising in automating the assessment of GUIs of web-based software systems. Yet, solutions for the assessment of mobile GUIs using machine learning are still unknown. Here we introduce a deep learning model to assess the visual aesthetics of mobile Android applications designed with App Inventor. We used a supervised learning approach to train and compare models using three different architectures. The highest performing model, a Resnet50, achieved a mean squared error of .022. The assessments of new GUIs showed an excellent correlation with human ratings (ρ = .9), and the Bland Altman plot analysis revealed 95% agreement with their labels. These results indicate the model’s effectiveness in automating the visual aesthetics assessment of GUIs of mobile apps.
- 8 March 2024
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 30 (1) , 102-115
Open AccessA Deep Learning Model for the Assessment of the Visual Aesthetics of Mobile User Interfaces
Visual aesthetics is one of the first aspects that users experience when looking at graphical user interfaces (GUIs), contributing to the perceived usability and credibility of a software system. It can also be an essential success factor in contexts where graphical elements play an important role in attracting users, such as choosing a mobile app from an app store. Therefore, visual aesthetics assessments are crucial in interface design, but traditional methods, involving target user representatives assessing each GUI individually, are costly and time-consuming. In this context, machine learning models have been demonstrated to be promising in automating the assessment of GUIs of web-based software systems. Yet, solutions for the assessment of mobile GUIs using machine learning are still unknown. Here we introduce a deep learning model to assess the visual aesthetics of mobile Android applications designed with App Inventor. We used a supervised learning approach to train and compare models using three different architectures. The highest performing model, a Resnet50, achieved a mean squared error of .022. The assessments of new GUIs showed an excellent correlation with human ratings (ρ = .9), and the Bland Altman plot analysis revealed 95% agreement with their labels. These results indicate the model’s effectiveness in automating the visual aesthetics assessment of GUIs of mobile apps.
- 5 January 2024
- Published by Springer Nature
- p. 1112-1119
MEEGA+, Systematic Model to Evaluate Educational Games
- 5 January 2024
- Published by Springer Nature
- p. 1112-1119
MEEGA+, Systematic Model to Evaluate Educational Games
- Open Access
- 18 December 2023
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 31, 1031-1056
Uma Análise Detalhada do Desempenho de Aprendizagem ensinando Machine Learning na Educação Básica aplicando a Teoria de Resposta ao Item
A atual inserção de Machine Learning (ML) no dia-a-dia demonstra a importância de introduzir o ensino de conceitos de ML desde a Educação Básica. Acompanhando esta tendência surge a necessidade de avaliar essa aprendizagem. Neste artigo apresentamos o projeto, desenvolvimento e implementação de um modelo de avaliação da aprendizagem de ML, com destaque para avaliação da validade e da confiabilidade da rubrica resultante. Essa rubrica visa avaliar a aprendizagem pelo desempenho do aluno com base nos resultados da aprendizagem da aplicação de conceitos de ML por alunos dos anos finais do Ensino Fundamental e do Ensino Médio. Adotando a Teoria de Resposta ao Item apresentamos uma proposta preliminar da construção de uma escala para o nível de aprendizagem dos estudantes. Os resultados da análise detalhada mostram que foi possível calibrar os parâmetros da Teoria de Resposta ao Item com índices satisfatórios de confiabilidade e validade, o que demonstra o potencial de utilização da rubrica de modo a auxiliar tanto alunos quanto pesquisadores e professores a promover o desenvolvimento do ensino de ML na Educação Básica.
- 18 December 2023
- Published by Sociedade Brasileira de Computação in Revista Brasileira de Informática na Educação
- Vol. 31, 1031-1056
Open AccessUma Análise Detalhada do Desempenho de Aprendizagem ensinando Machine Learning na Educação Básica aplicando a Teoria de Resposta ao Item
A atual inserção de Machine Learning (ML) no dia-a-dia demonstra a importância de introduzir o ensino de conceitos de ML desde a Educação Básica. Acompanhando esta tendência surge a necessidade de avaliar essa aprendizagem. Neste artigo apresentamos o projeto, desenvolvimento e implementação de um modelo de avaliação da aprendizagem de ML, com destaque para avaliação da validade e da confiabilidade da rubrica resultante. Essa rubrica visa avaliar a aprendizagem pelo desempenho do aluno com base nos resultados da aprendizagem da aplicação de conceitos de ML por alunos dos anos finais do Ensino Fundamental e do Ensino Médio. Adotando a Teoria de Resposta ao Item apresentamos uma proposta preliminar da construção de uma escala para o nível de aprendizagem dos estudantes. Os resultados da análise detalhada mostram que foi possível calibrar os parâmetros da Teoria de Resposta ao Item com índices satisfatórios de confiabilidade e validade, o que demonstra o potencial de utilização da rubrica de modo a auxiliar tanto alunos quanto pesquisadores e professores a promover o desenvolvimento do ensino de ML na Educação Básica.