Andrey Pimentel | Universidade Federal do Paraná (original) (raw)
Papers by Andrey Pimentel
Anais do XXXIII Simpósio Brasileiro de Informática na Educação (SBIE 2022)
The use of multiple external representations (MER) in the empowerment of executive functions (EF)... more The use of multiple external representations (MER) in the empowerment of executive functions (EF) was identified and characterized through a systematic mapping. EF are part of the human learning triad, contributing to the development of complex executive skills. Learners may have difficulty developing EF, and can benefit from MER. Data from 18 articles were extracted. Most MER systems used two external representations, verbal-textual and visual-graphical, through desktop applications. In relation to EF, the most considered component was working memory. We identified the need for further research that considers the effects of MERs on cognitive flexibility and inhibition, and the impact of mobile devices to the exhibition of MERs.
Learning styles (LS) refer to the ways and forms that the student prefers to learn in the teachin... more Learning styles (LS) refer to the ways and forms that the student prefers to learn in the teaching and learning process. Each student has their own way of receiving and processing information, and bearing in mind the learning style is important to better understand their individual preferences and to understand why certain teaching methods and techniques work better for some students, while for others they do not. We believe that knowledge of these styles enables the possibility of making propositions for teaching, thus reorganizing teaching methods and techniques in order to allow learning that is adapted to the individual needs of the student. This would be possible through the creation of online educational resources adapted to the style of the student. In this context, this article presents the structure of a learning object interface adaptation based on the learning style. This should enable the creation of the adapted learning object according to the student's learning sty...
O uso de conceitos presentes em Sistemas Tutores Inteligentes vem crescendo em objetos de aprendi... more O uso de conceitos presentes em Sistemas Tutores Inteligentes vem crescendo em objetos de aprendizagem (OA), em especial a remediacao de erros. O destaque deste estudo vai alem do uso de conceitos de STI e explora a eficiencia do uso das Multiplas Representacoes Externas (MREs) na remediacao de erros. Assim, o presente artigo apresenta o modelo arquitetural, os conceitos pertinentes a classificacao de erros matematicos e das Multiplas Representacoes Externas. Bem como a aplicacao contextualizada de um experimento a partir do desenvolvimento do OA matematico para o aprendizado do Teorema de Pitagoras. Em seguida e apresentado a aplicacao de um experimento com uso de pre-teste e pos-teste, a fim de validar a eficiencia do uso de Remediacao de Erros matematicos com o uso de MRE junto uma a escola da rede publica de ensino do estado do Parana, em uma turma de 9o ano.
Many works in the literature show that positive emotions improve learning. However, in the educat... more Many works in the literature show that positive emotions improve learning. However, in the educational context, the affective dimension is often not adopted in the teaching-learning process. One of them is that there are many students for a teacher, making the practice of adapting the didactics and individualized feedbacks practically impossible. The low or sometimes no emotion analysis of those involved in learning also becomes a obstacle. One possibility to circumvent this problem is the use of Intelligent Tutoring Systems (ITS), to understand the student individually and adapt environments according to their use. It also adds the theories of emotions so that the ITS can understand the affective dimension of the student during activities. This paper aims to present a way to infer changes in a student’s affective states to improve feedbacks in ITS For this, facial expressions and brain waves (using a low-cost equipment called openBCI) were studied for acquisition and emotions. In t...
In this document we present several aspects that justify the need to use multiple external repres... more In this document we present several aspects that justify the need to use multiple external representations in an intelligent tutoring system in order to remediate the student's errors. The main purpose of this research is present a tutor constructed over the repair theory. No work has been found in the scientific literature that put together the repair theory and multiple external representations, aiming the error remediation. A study of important concepts and definitions in the field of intelligent tutoring systems, learning theories, multiple external representations and classifications of mathematical errors was conducted. Based on this study, an intelligent tutor was developed for teaching of the subtraction, detailing its architecture and operation. Finally, we present our conclusions.
There are nowadays a strong agreement in the research community that emotions directly impact lea... more There are nowadays a strong agreement in the research community that emotions directly impact learning. Then, an important feature for a software that claim to be useful for learning is to deal with students’ affective reactions. These software should be able to adapt to the users’ affective reactions, trying to get a more natural human-computer interaction. Some priors works achieved relative success in inferring students’ emotion. However, most of them, rely on intrusive, expensive or little practical sensors that track students’ physical reactions. This paper presents as its main contribution the proposal of a hybrid model for emotion inference, combining physical and cognitive elements, using cheaper and little intrusive method to collect data. First experiments with students in a traditional classroom demonstrated the feasibility of this proposal and also indicated promising results for inference of learning centered emotions. In these experiments we achieve an accuracy rate an...
Intelligent Tutoring Systems, 2018
Researches in areas such as neuroscience and psychology indicate that emotions directly impact le... more Researches in areas such as neuroscience and psychology indicate that emotions directly impact learning. So, adapting to the learners’ affective reactions became a requirement and also a challenge for building a new generation of affect aware computing learning environments. In this paper, we present a hybrid approach for inferring learning related emotion that combines cognitive and physical data, gathered using minimal or non intrusive methods. In an initial experiment with students in a real education environment it was possible to obtain promising results when comparing some usual performance metrics with correlated works. In this study we achieved accuracy rates and Cohen’s Kappa near to 65% and 0.55, respectively. Furthermore, considering the open and expansible nature of this proposal, we believe that this results could be improved in the future by adding new data or new sensors to the model, for example.
Anais do XXXI Simpósio Brasileiro de Informática na Educação (SBIE 2020), 2020
O processo de ensino e aprendizagem realizado de forma virtual tem sido muito difundido atualment... more O processo de ensino e aprendizagem realizado de forma virtual tem sido muito difundido atualmente por meio dos Sistemas Tutores Inteligentes (STI), pois podem prover instruções imediatas e personalizadas aos aprendizes. Essa personalização pode considerar o estado afetivo do aprendiz para aperfeiçoar as estratégias de ensino. Neste trabalho é apresentado um modelo de intervenção tutorial com base na identificação do tipo de erro matemático cometido pelo aprendiz. Para avaliar o modelo um experimento com aprendizes foi realizado e por meio da inferência dos estados afetivos os resultados indicam que as intervenções personalizadas favorecem um maior engajamento e motivação em relação às intervenções mínimas.
Proceedings of the 15th International Conference on Enterprise Information Systems, 2013
The proposition of error remediation is a widely used feature in Intelligent Tutoring Systems, bu... more The proposition of error remediation is a widely used feature in Intelligent Tutoring Systems, but the use of Multiple External Representations to assist it, is a research subject. This paper presents (or discuss) the use of Multiple External Representations contribution in error remediation in Learning Objects. To perform this study, we present an architectural model, a conceptual framework for mathematical error classification and Multiple External Representations, using a cognitive remediation for errors. Following is presented the application of contextual remediation of error based on Multiple External Representations in a Learning Object. And finally, we present the performance of students during the application of an experiment consisting of the following steps: pre-test, test and post-test.
Revista Brasileira de Informática na Educação, 2016
A aprendizagem de Matemática tem intrigado pesquisadores e educadores há muito tempo, principalme... more A aprendizagem de Matemática tem intrigado pesquisadores e educadores há muito tempo, principalmente no que se refere a erros conceituais. Apesar dos avanços das tecnologias digitais no tratamento de erros da aprendizagem, poucos resultados concretos foram atingidos. Mais recentemente, os institutos oficiais de avaliação escolar do Brasil apontaram limitações no aprendizado do Matemática, principalmente no ensino médio. Assim, a criação de métodos inovadores e ferramentas de software de apoio pedagógico que ajudem tanto o aprendiz como o professor a revisitarem os erros cometidos passa a ser uma perspectiva relevante de pesquisa. Este artigo apresenta um método e uma ferramenta web (FARMA) de autoria e aprendizagem com enfoque nas ideias de retroação a contextos de erro e mobilidade tecnológico-educacional. A metáfora de retroação ao contexto de um erro do aprendiz se constitui na abordagem cognitivista do projeto e implementação da FARMA. Com ela, aprendizes e professores podem se ...
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2011
This article discusses the contribution of mathematical errors classification in Learning Objects... more This article discusses the contribution of mathematical errors classification in Learning Objects development. Here is proposed a remediation approach of learners erros through external representations for the acquisition of a mathematical concepts. This article presents: a compilation of ratings types of errors observed in learning mathematics, the relationships between these types of errors and the functions of Multiple External Representations and proposes a conceptual framework for remediation of learners errors interacting with intelligent tutoring systems using the Multiple External Representations. Resumo. Este artigo discute a contribuição da classificação de erros matemáticos no desenvolvimento de Objetos de Aprendizagem. É proposto apresentar uma abordagem para a remediação de erros dos aprendizes através de representações externas para aquisição de conceitos matemáticos. Neste artigo é apresentada uma compilação de classificações de tipos de erros observados para o aprendizado de matemática, as relações entre estes tipos de erros e as funções das Múltiplas Representações Externas e é proposto um arcabouço conceitual para remediação de erros de aprendizes interagindo com Sistemas Tutores Inteligentes usando as Múltiplas Representações Externas.
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2012
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2012
Anais do XXVI Simpósio Brasileiro de Informática na Educação (SBSI 2015), 2015
Learning styles refer to preferences regarding ways and forms that the student prefers to learn. ... more Learning styles refer to preferences regarding ways and forms that the student prefers to learn. The knowledge of these styles allows propositions for teaching rearranging instructional methods and learning strategies to enable more adapted to individual student learning needs. In this context, this article presents a metamodel categorization of learning styles to help with the mapping of the preferences and characteristics of the styles that can be used to provide adaptation to the presentation of the learning object (LO) according to the student's learning style. Resumo. Os estilos de aprendizagem referem-se a preferências em relação aos modos e formas que o aluno prefere aprender. O conhecimento desses estilos permite fazer proposições para o ensino rearranjando os métodos instrucionais e as estratégias de aprendizagem para possibilitar uma aprendizagem mais adaptada as necessidades individuais do aluno. Neste contexto, este artigo apresenta um metamodelo de categorização de estilos de aprendizagem para ajudar no mapeamento das preferências e características dos estilos que podem ser usadas para proporcionar adaptação na apresentação do objeto de aprendizagem (OA) de acordo com o estilo de aprendizagem do aluno.
The aim of this paper is model computationally the representational levels of the Model Represent... more The aim of this paper is model computationally the representational levels of the Model Representational Redescription, proposed by Karmiloff-Smith, in structures of answers. The correlation between the representational levels and structures of responses is based on the characteristics of relation, storage and processing of representations. The structures selected for mapping responses are alternatives, correlation of items, filling gaps and multiple choices with explanations of the choices.
Computer Networks, 2015
A MapReduce framework abstracts distributed system issues, integrating a distributed file system ... more A MapReduce framework abstracts distributed system issues, integrating a distributed file system with an application's needs. However, the lack of determinism in distributed system components and reliability in the network may cause applications errors that are difficult to identify, find, and correct. This paper presents a method to create a set of fault cases, derived from a Petri net (PN), and a framework to automate the execution of these fault cases in a distributed system. The framework controls each MapReduce component and injects faults according to the component's state. Experimental results showed the fault cases are representative for testing Hadoop, a MapReduce implementation. We tested three versions of Hadoop and identified bugs and elementary behavioral differences between the versions. The method provides network reliability enhancements as a byproduct because it identifies errors caused by a service or system bug instead of simply assigning them to the network.
Revista Brasileira de Informática na Educaçao ( …, 1998
Proceedings of the XXXIII Brazilian Symposium on Software Engineering, 2019
The representation of contexts is essential in tasks involving Natural Language Processing (NLP).... more The representation of contexts is essential in tasks involving Natural Language Processing (NLP). In the field of software engineering, classifying similar texts within a specific context has been a complex task, considering the informality and the complexity inherent of the texts produced through many software development processes (e.g. agile methods). Word embeddings capture semantic and syntactic information about unique words, allowing them to be represented in a dense and low-dimensional format. This property makes the embeddings vectors an important input feature for machine learning algorithms that aim to classify texts. Although there has been much research around the application of word embeddings in several areas, up to this moment, there is no knowledge about studies that have explored its application in the creation of a specific model for the domain of the area of software engineering. Thus, this article presents the proposal to generate an embedding model, called embeddings model for software engineering (EmbSE), which can recognize specific and relevant terms in the software engineering context. This model can be used as the main entry in the classification of several textual artifacts generated during the software development project process. The results are promising, presenting a 48% improvement in the mAP values for the EmbSE concerning the model trained on the generic corpus. This reinforces the hypothesis that a model of this nature can bring significant improvements in the classification of texts of the area.
Anais do XXVIII Simpósio Brasileiro de Informática na Educação (SBIE 2017), 2017
The progress and popularity of Distance Learning has generated a greater demand for the use of in... more The progress and popularity of Distance Learning has generated a greater demand for the use of increasingly effective methods of teaching and learning. One of the biggest challenges is the increased need to adapt to specific characteristics of each individual learner. This paper presents an automated alternative to identify which Learning Style suits each student. The presented model IPP allows us to identify each student's Personality Profile by using the information in the open texts elaborated by each learner, giving us an inference for which Learning Style is more suited to each case. Resumo. O avanço e popularização da Educação a Distância tem gerado uma demanda maior na utilização de métodos cada vez mais eficientes de ensino e aprendizagem. Um dos desafios encontradosé a maior necessidade de adaptaçãoàs particularidades individuais dos alunos. Este trabalho apresenta uma alternativa automatizada para a identificação do Estilo de Aprendizagem de alunos. A proposta apresenta o Modelo de Identificação de Perfil de Personalidade (IPP), que utiliza as informações presentes nos textos livres elaborados pelos alunos, permitindo a inferência de um Estilo de Aprendizagem mais adequado a cada caso.
Anais do XXVIII Simpósio Brasileiro de Informática na Educação (SBIE 2017), 2017
Infer emotional states is currently regarded as a challenge to the development of emotion aware a... more Infer emotional states is currently regarded as a challenge to the development of emotion aware adaptive educational software. In this paper a hybrid model of emotions inference is proposed based on two components: cognitive and physical. Initial essays show promising results with the application of this approach. The experiment presented shows how a neutral reaction in the physical component (facial expression) influences the positive inference of cognitive component (correct answer). Resumo. Inferir estados afetivos é ainda um desafio para o desenvolvimento de softwares educacionais adaptativos às reações emocionais dos aprendizes. Neste trabalho é proposto um modelo híbrido de inferência de emoções baseado na fusão de dois componentes: cognitivo e físico. Experimentos iniciais demonstram resultados promissores com a aplicação desta abordagem. O experimento apresentado demonstra como uma reação neutra no componente físico (expressão facial) influencia a inferência positiva do componente cognitivo (acerto de questão).
Anais do XXXIII Simpósio Brasileiro de Informática na Educação (SBIE 2022)
The use of multiple external representations (MER) in the empowerment of executive functions (EF)... more The use of multiple external representations (MER) in the empowerment of executive functions (EF) was identified and characterized through a systematic mapping. EF are part of the human learning triad, contributing to the development of complex executive skills. Learners may have difficulty developing EF, and can benefit from MER. Data from 18 articles were extracted. Most MER systems used two external representations, verbal-textual and visual-graphical, through desktop applications. In relation to EF, the most considered component was working memory. We identified the need for further research that considers the effects of MERs on cognitive flexibility and inhibition, and the impact of mobile devices to the exhibition of MERs.
Learning styles (LS) refer to the ways and forms that the student prefers to learn in the teachin... more Learning styles (LS) refer to the ways and forms that the student prefers to learn in the teaching and learning process. Each student has their own way of receiving and processing information, and bearing in mind the learning style is important to better understand their individual preferences and to understand why certain teaching methods and techniques work better for some students, while for others they do not. We believe that knowledge of these styles enables the possibility of making propositions for teaching, thus reorganizing teaching methods and techniques in order to allow learning that is adapted to the individual needs of the student. This would be possible through the creation of online educational resources adapted to the style of the student. In this context, this article presents the structure of a learning object interface adaptation based on the learning style. This should enable the creation of the adapted learning object according to the student's learning sty...
O uso de conceitos presentes em Sistemas Tutores Inteligentes vem crescendo em objetos de aprendi... more O uso de conceitos presentes em Sistemas Tutores Inteligentes vem crescendo em objetos de aprendizagem (OA), em especial a remediacao de erros. O destaque deste estudo vai alem do uso de conceitos de STI e explora a eficiencia do uso das Multiplas Representacoes Externas (MREs) na remediacao de erros. Assim, o presente artigo apresenta o modelo arquitetural, os conceitos pertinentes a classificacao de erros matematicos e das Multiplas Representacoes Externas. Bem como a aplicacao contextualizada de um experimento a partir do desenvolvimento do OA matematico para o aprendizado do Teorema de Pitagoras. Em seguida e apresentado a aplicacao de um experimento com uso de pre-teste e pos-teste, a fim de validar a eficiencia do uso de Remediacao de Erros matematicos com o uso de MRE junto uma a escola da rede publica de ensino do estado do Parana, em uma turma de 9o ano.
Many works in the literature show that positive emotions improve learning. However, in the educat... more Many works in the literature show that positive emotions improve learning. However, in the educational context, the affective dimension is often not adopted in the teaching-learning process. One of them is that there are many students for a teacher, making the practice of adapting the didactics and individualized feedbacks practically impossible. The low or sometimes no emotion analysis of those involved in learning also becomes a obstacle. One possibility to circumvent this problem is the use of Intelligent Tutoring Systems (ITS), to understand the student individually and adapt environments according to their use. It also adds the theories of emotions so that the ITS can understand the affective dimension of the student during activities. This paper aims to present a way to infer changes in a student’s affective states to improve feedbacks in ITS For this, facial expressions and brain waves (using a low-cost equipment called openBCI) were studied for acquisition and emotions. In t...
In this document we present several aspects that justify the need to use multiple external repres... more In this document we present several aspects that justify the need to use multiple external representations in an intelligent tutoring system in order to remediate the student's errors. The main purpose of this research is present a tutor constructed over the repair theory. No work has been found in the scientific literature that put together the repair theory and multiple external representations, aiming the error remediation. A study of important concepts and definitions in the field of intelligent tutoring systems, learning theories, multiple external representations and classifications of mathematical errors was conducted. Based on this study, an intelligent tutor was developed for teaching of the subtraction, detailing its architecture and operation. Finally, we present our conclusions.
There are nowadays a strong agreement in the research community that emotions directly impact lea... more There are nowadays a strong agreement in the research community that emotions directly impact learning. Then, an important feature for a software that claim to be useful for learning is to deal with students’ affective reactions. These software should be able to adapt to the users’ affective reactions, trying to get a more natural human-computer interaction. Some priors works achieved relative success in inferring students’ emotion. However, most of them, rely on intrusive, expensive or little practical sensors that track students’ physical reactions. This paper presents as its main contribution the proposal of a hybrid model for emotion inference, combining physical and cognitive elements, using cheaper and little intrusive method to collect data. First experiments with students in a traditional classroom demonstrated the feasibility of this proposal and also indicated promising results for inference of learning centered emotions. In these experiments we achieve an accuracy rate an...
Intelligent Tutoring Systems, 2018
Researches in areas such as neuroscience and psychology indicate that emotions directly impact le... more Researches in areas such as neuroscience and psychology indicate that emotions directly impact learning. So, adapting to the learners’ affective reactions became a requirement and also a challenge for building a new generation of affect aware computing learning environments. In this paper, we present a hybrid approach for inferring learning related emotion that combines cognitive and physical data, gathered using minimal or non intrusive methods. In an initial experiment with students in a real education environment it was possible to obtain promising results when comparing some usual performance metrics with correlated works. In this study we achieved accuracy rates and Cohen’s Kappa near to 65% and 0.55, respectively. Furthermore, considering the open and expansible nature of this proposal, we believe that this results could be improved in the future by adding new data or new sensors to the model, for example.
Anais do XXXI Simpósio Brasileiro de Informática na Educação (SBIE 2020), 2020
O processo de ensino e aprendizagem realizado de forma virtual tem sido muito difundido atualment... more O processo de ensino e aprendizagem realizado de forma virtual tem sido muito difundido atualmente por meio dos Sistemas Tutores Inteligentes (STI), pois podem prover instruções imediatas e personalizadas aos aprendizes. Essa personalização pode considerar o estado afetivo do aprendiz para aperfeiçoar as estratégias de ensino. Neste trabalho é apresentado um modelo de intervenção tutorial com base na identificação do tipo de erro matemático cometido pelo aprendiz. Para avaliar o modelo um experimento com aprendizes foi realizado e por meio da inferência dos estados afetivos os resultados indicam que as intervenções personalizadas favorecem um maior engajamento e motivação em relação às intervenções mínimas.
Proceedings of the 15th International Conference on Enterprise Information Systems, 2013
The proposition of error remediation is a widely used feature in Intelligent Tutoring Systems, bu... more The proposition of error remediation is a widely used feature in Intelligent Tutoring Systems, but the use of Multiple External Representations to assist it, is a research subject. This paper presents (or discuss) the use of Multiple External Representations contribution in error remediation in Learning Objects. To perform this study, we present an architectural model, a conceptual framework for mathematical error classification and Multiple External Representations, using a cognitive remediation for errors. Following is presented the application of contextual remediation of error based on Multiple External Representations in a Learning Object. And finally, we present the performance of students during the application of an experiment consisting of the following steps: pre-test, test and post-test.
Revista Brasileira de Informática na Educação, 2016
A aprendizagem de Matemática tem intrigado pesquisadores e educadores há muito tempo, principalme... more A aprendizagem de Matemática tem intrigado pesquisadores e educadores há muito tempo, principalmente no que se refere a erros conceituais. Apesar dos avanços das tecnologias digitais no tratamento de erros da aprendizagem, poucos resultados concretos foram atingidos. Mais recentemente, os institutos oficiais de avaliação escolar do Brasil apontaram limitações no aprendizado do Matemática, principalmente no ensino médio. Assim, a criação de métodos inovadores e ferramentas de software de apoio pedagógico que ajudem tanto o aprendiz como o professor a revisitarem os erros cometidos passa a ser uma perspectiva relevante de pesquisa. Este artigo apresenta um método e uma ferramenta web (FARMA) de autoria e aprendizagem com enfoque nas ideias de retroação a contextos de erro e mobilidade tecnológico-educacional. A metáfora de retroação ao contexto de um erro do aprendiz se constitui na abordagem cognitivista do projeto e implementação da FARMA. Com ela, aprendizes e professores podem se ...
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2011
This article discusses the contribution of mathematical errors classification in Learning Objects... more This article discusses the contribution of mathematical errors classification in Learning Objects development. Here is proposed a remediation approach of learners erros through external representations for the acquisition of a mathematical concepts. This article presents: a compilation of ratings types of errors observed in learning mathematics, the relationships between these types of errors and the functions of Multiple External Representations and proposes a conceptual framework for remediation of learners errors interacting with intelligent tutoring systems using the Multiple External Representations. Resumo. Este artigo discute a contribuição da classificação de erros matemáticos no desenvolvimento de Objetos de Aprendizagem. É proposto apresentar uma abordagem para a remediação de erros dos aprendizes através de representações externas para aquisição de conceitos matemáticos. Neste artigo é apresentada uma compilação de classificações de tipos de erros observados para o aprendizado de matemática, as relações entre estes tipos de erros e as funções das Múltiplas Representações Externas e é proposto um arcabouço conceitual para remediação de erros de aprendizes interagindo com Sistemas Tutores Inteligentes usando as Múltiplas Representações Externas.
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2012
Anais Do Simposio Brasileiro De Informatica Na Educacao, 2012
Anais do XXVI Simpósio Brasileiro de Informática na Educação (SBSI 2015), 2015
Learning styles refer to preferences regarding ways and forms that the student prefers to learn. ... more Learning styles refer to preferences regarding ways and forms that the student prefers to learn. The knowledge of these styles allows propositions for teaching rearranging instructional methods and learning strategies to enable more adapted to individual student learning needs. In this context, this article presents a metamodel categorization of learning styles to help with the mapping of the preferences and characteristics of the styles that can be used to provide adaptation to the presentation of the learning object (LO) according to the student's learning style. Resumo. Os estilos de aprendizagem referem-se a preferências em relação aos modos e formas que o aluno prefere aprender. O conhecimento desses estilos permite fazer proposições para o ensino rearranjando os métodos instrucionais e as estratégias de aprendizagem para possibilitar uma aprendizagem mais adaptada as necessidades individuais do aluno. Neste contexto, este artigo apresenta um metamodelo de categorização de estilos de aprendizagem para ajudar no mapeamento das preferências e características dos estilos que podem ser usadas para proporcionar adaptação na apresentação do objeto de aprendizagem (OA) de acordo com o estilo de aprendizagem do aluno.
The aim of this paper is model computationally the representational levels of the Model Represent... more The aim of this paper is model computationally the representational levels of the Model Representational Redescription, proposed by Karmiloff-Smith, in structures of answers. The correlation between the representational levels and structures of responses is based on the characteristics of relation, storage and processing of representations. The structures selected for mapping responses are alternatives, correlation of items, filling gaps and multiple choices with explanations of the choices.
Computer Networks, 2015
A MapReduce framework abstracts distributed system issues, integrating a distributed file system ... more A MapReduce framework abstracts distributed system issues, integrating a distributed file system with an application's needs. However, the lack of determinism in distributed system components and reliability in the network may cause applications errors that are difficult to identify, find, and correct. This paper presents a method to create a set of fault cases, derived from a Petri net (PN), and a framework to automate the execution of these fault cases in a distributed system. The framework controls each MapReduce component and injects faults according to the component's state. Experimental results showed the fault cases are representative for testing Hadoop, a MapReduce implementation. We tested three versions of Hadoop and identified bugs and elementary behavioral differences between the versions. The method provides network reliability enhancements as a byproduct because it identifies errors caused by a service or system bug instead of simply assigning them to the network.
Revista Brasileira de Informática na Educaçao ( …, 1998
Proceedings of the XXXIII Brazilian Symposium on Software Engineering, 2019
The representation of contexts is essential in tasks involving Natural Language Processing (NLP).... more The representation of contexts is essential in tasks involving Natural Language Processing (NLP). In the field of software engineering, classifying similar texts within a specific context has been a complex task, considering the informality and the complexity inherent of the texts produced through many software development processes (e.g. agile methods). Word embeddings capture semantic and syntactic information about unique words, allowing them to be represented in a dense and low-dimensional format. This property makes the embeddings vectors an important input feature for machine learning algorithms that aim to classify texts. Although there has been much research around the application of word embeddings in several areas, up to this moment, there is no knowledge about studies that have explored its application in the creation of a specific model for the domain of the area of software engineering. Thus, this article presents the proposal to generate an embedding model, called embeddings model for software engineering (EmbSE), which can recognize specific and relevant terms in the software engineering context. This model can be used as the main entry in the classification of several textual artifacts generated during the software development project process. The results are promising, presenting a 48% improvement in the mAP values for the EmbSE concerning the model trained on the generic corpus. This reinforces the hypothesis that a model of this nature can bring significant improvements in the classification of texts of the area.
Anais do XXVIII Simpósio Brasileiro de Informática na Educação (SBIE 2017), 2017
The progress and popularity of Distance Learning has generated a greater demand for the use of in... more The progress and popularity of Distance Learning has generated a greater demand for the use of increasingly effective methods of teaching and learning. One of the biggest challenges is the increased need to adapt to specific characteristics of each individual learner. This paper presents an automated alternative to identify which Learning Style suits each student. The presented model IPP allows us to identify each student's Personality Profile by using the information in the open texts elaborated by each learner, giving us an inference for which Learning Style is more suited to each case. Resumo. O avanço e popularização da Educação a Distância tem gerado uma demanda maior na utilização de métodos cada vez mais eficientes de ensino e aprendizagem. Um dos desafios encontradosé a maior necessidade de adaptaçãoàs particularidades individuais dos alunos. Este trabalho apresenta uma alternativa automatizada para a identificação do Estilo de Aprendizagem de alunos. A proposta apresenta o Modelo de Identificação de Perfil de Personalidade (IPP), que utiliza as informações presentes nos textos livres elaborados pelos alunos, permitindo a inferência de um Estilo de Aprendizagem mais adequado a cada caso.
Anais do XXVIII Simpósio Brasileiro de Informática na Educação (SBIE 2017), 2017
Infer emotional states is currently regarded as a challenge to the development of emotion aware a... more Infer emotional states is currently regarded as a challenge to the development of emotion aware adaptive educational software. In this paper a hybrid model of emotions inference is proposed based on two components: cognitive and physical. Initial essays show promising results with the application of this approach. The experiment presented shows how a neutral reaction in the physical component (facial expression) influences the positive inference of cognitive component (correct answer). Resumo. Inferir estados afetivos é ainda um desafio para o desenvolvimento de softwares educacionais adaptativos às reações emocionais dos aprendizes. Neste trabalho é proposto um modelo híbrido de inferência de emoções baseado na fusão de dois componentes: cognitivo e físico. Experimentos iniciais demonstram resultados promissores com a aplicação desta abordagem. O experimento apresentado demonstra como uma reação neutra no componente físico (expressão facial) influencia a inferência positiva do componente cognitivo (acerto de questão).