Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)最新文献

{"title":"Deep Learning para Previsão do Desempenho do Estudante: Um Mapeamento Sistemático da Literatura","authors":"Nilcimar Neitzel Will, Avanilde Kemczinski, R. Parpinelli","doi":"10.5753/cbie.sbie.2019.1798","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.1798","url":null,"abstract":"It is not of today that school dropout has been a problem, both in presential environments and in virtual learning environments. Affecting not only the career of the students but also the educational institutions. Predicting student performance helps institutions identify the factors that lead to evasion, and to take measures for student retention at school. This work seeks to study how Deep Learning has been applied in predicting student performance, and to identify how it has been implemented, techniques, methods, algorithms, and tools. Resumo. Não é de hoje que a evasão escolar tem sido um problema, tanto em ambientes presenciais, quanto em ambientes virtuais de aprendizagem. Afetando não apenas a carreira dos estudantes, como também as instituições de ensino. Prever o desempenho do aluno ajuda as instituições a identificar os fatores que levam a evasão, e assim tomar medidas para a retenção do aluno na escola. Este trabalho busca estudar como o Deep Learning tem sido aplicado na previsão do desempenho do estudante, e identificar como ele tem sido implementado, as técnicas, métodos, algoritmos e ferramentas.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123560693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revisitando um Jogo Educacional para desenvolver o Pensamento Computacional com Gramática de Grafos","authors":"B. Junior, S. Cavalheiro, Luciana Foss","doi":"10.5753/cbie.sbie.2019.863","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.863","url":null,"abstract":"","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122360256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mineração de Padrões Sequenciais de Sentimentos: Um Estudo de Caso na Detecção de Propensão à Evasão Escolar na Educação Superior","authors":"T. P. Pimentel, Claudio Passos, Isabel Fernandes, R. Goldschmidt","doi":"10.5753/cbie.sbie.2019.1411","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.1411","url":null,"abstract":"","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129974986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Qual Técnica de Learning Analytics Usar para Prever o Desempenho Acadêmico de Estudantes? Uma Análise Comparativa Experimental com Dados de MOOCs","authors":"W. Silva, Marcelo de Oliveira Costa Machado, S. Siqueira","doi":"10.5753/cbie.sbie.2019.1391","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.1391","url":null,"abstract":"Predicting student academic performance is one of the main research topics in Learning Analytics, for which different techniques have been applied. In order to facilitate the choice of a technique, this study presents a comparative analysis among regression and classification techniques, considering different application scenarios. We used data from MITx/HarvardX containing logs of activities and participation of 15 groups of 12 MOOCs. Results obtained from the performance evaluation metrics suggest the choice of Decision Trees as a technique to build models for regression and a choice between Decision Trees and Support Vector Machines to build models for classification. Resumo. A previsão do desempenho acadêmico de estudantes é um dos principais tópicos de pesquisa em Learning Analytics, para o qual diferentes técnicas foram aplicadas. De modo a facilitar a escolha de uma técnica, este estudo apresenta uma análise comparativa entre técnicas de regressão e classificação, considerando diferentes cenários de aplicação. Foram utilizados dados do MITx/HarvardX contendo logs de atividades e participação de 15 turmas de 12 MOOCs. Os resultados obtidos, a partir das métricas de avaliação de performance, sugerem a escolha de Árvores de Decisão como técnica para criação de modelos para regressão e uma escolha entre Árvores de Decisão e Support Vector Machines para a criação de modelos de classificação. 1. Introdução O crescente volume de dados gerados em diferentes atividades educacionais, sobretudo em ambientes de educação a distância ou de apoio ao ensino presencial, reforça o interesse de pesquisa em Learning Analytics (LA). De maneira ampla, LA estuda a aplicação de técnicas de análise de dados para compreender e otimizar o processo de ensinoaprendizagem bem como o ambiente em que ele ocorre [Gašević et al. 2015]. A previsão de desempenho acadêmico dos estudantes está entre os principais temas de pesquisa em LA [Gašević et al. 2016] e pode ser abordada através de perspectivas como a identificação de estudantes sob risco de evasão, tendências de reprovação e até mesmo como a previsão de notas finais. 1 O termo Learning Analytics é utilizado neste trabalho para o contexto geral da área de pesquisa, sem fazer distinção com Educational Analytics, Teaching Analytics ou Academic Analytics. DOI: 10.5753/cbie.sbie.2019.1391 1391 Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019) VIII Congresso Brasileiro de Informática na Educação (CBIE 2019)","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129986670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analyzing the Impact of Programming Mistakes on Students' Programming Abilities","authors":"A. Junior, Jorge Figueiredo, D. Serey","doi":"10.5753/cbie.sbie.2019.369","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.369","url":null,"abstract":"Despite all the research on students misconceptions in introductory programming courses, there is still a lot to understand about how they make and correct mistakes. The reviewed works investigate code as a final, static artifact, but this does not tell the whole story about the students’ mistakes. With this study, we take the first step toward an attempt to close this gap. By capturing granular states of the coding process, we collected and analyzed data in an experiment with twenty-two novice students aged 14 to 16. With the experiment, we found the most common issues in the students’ code. This enabled us to know which mistakes may prevent them from reaching a correct solution, and which will not interfere but may show an understanding problem in core programming concepts. This experiment precedes the development of an approach to help the teacher or teaching assistant in providing personalized and directed help to the students in programming courses.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130478939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Augmenting Teachers with Data Science Powers: Joining Human and Artificial Intelligence to Assist Students","authors":"R. Paiva, Júlio Ferreira Silva de Holanda, Myron David Peixoto, João Vieira","doi":"10.5753/cbie.sbie.2019.1721","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.1721","url":null,"abstract":"Technology has the potential to influence the processes and outcomes of teaching and learning. Researchers notice a high demand for online education, but these environments generate educational data in high quantity, diversity and velocity, which requires the use of technology. However, putting too much emphasis on artificial intelligence is not bringing the expected results. It is time to position teachers as the principal decision-makers in the “classroom” and use AI as an assistant. Our proposal is a tool (called T-Partner) to help online teachers: (1) search for relevant patterns in the educational data; (2) created visualisations to present the results in a more teacher-friendly way; (3) recommend study plans, based on students’ needs. For that, we applied data science techniques on these data and processed the results, making it easier for teachers to understand them. We evaluated the tool, asking participants to use it to complete some tasks that simulate a teacher analysing data to make pedagogical decisions. We evaluated time, correctness, number of doubts and the participants’ perceptions. The results show that most participants were able to complete the tasks in an appropriate amount of time and considered the T-Partner useful and easy to use in an online learning context.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130953266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Giving Automated Feedback About Student Code Identifiers: a Method Based on the Description of Programming Problem","authors":"Marcos Nascimento, Eliane Araújo, D. Serey, Jorge Figueiredo","doi":"10.5753/cbie.sbie.2019.537","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.537","url":null,"abstract":". Providing timely feedback on identifier naming to novice program-mers can help them to improve their program readability. However, due to the growth in the number of students learning to program nowadays, giving manual feedback on identifier quality become prohibitive. In this paper, we propose a method to automatically give this feedback which is correct 75.0% of the time in contrast to the instructors’ assessment. We found that 51.7% of the students who received automated feedback showed their program identifier quality improvement by picking better names. It means that we can help students to improve identifier naming and consequently, their program readability from early coding experiences.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131308503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rationale in Forum Discussions as Support for Software Upgrading of Online Course Platforms","authors":"Tiago Clementino, A. Moura","doi":"10.5753/cbie.sbie.2019.349","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.349","url":null,"abstract":"In online course software platforms, the forum may be an important instrument for feedback on pedagogical aspects. Students’ and instructors’ evaluations spontaneously shared in the forum – in terms of criticism, recommendations or requests – may also regard the platform’s software tools. These evaluations resemble what is called “rationale”, a useful concept from Software Engineering. This paper presents an exploratory study about mining spontaneous user rationale in Massive Open Online Course forum discussions. Results provide qualitative evidence that rationale can be an instrument to collect requirements for the evolution of support software in online educational platforms.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116913875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Um estudo de Interação a Longo Prazo com Aulas de Matemática usando Robôs","authors":"Maria Luíza Telles, Adam Moreira, R. Romero","doi":"10.5753/cbie.sbie.2019.626","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.626","url":null,"abstract":"The inclusion of the robotics for academic activities is already well established, with good results around the world. However, is robotics really effective in preschool, especially when children have a lasting interaction with the robot? This paper is focused on develop logical, cognitive and mathematical reasoning of 5 and 6 years-old children with the same robot along one and half year. The objective is to analyze if they learned the content approached, and to understand when and why the student loses the interest in classes. The results shown that, for the long-term interaction, it is necessary to focus on four variables: approached manner, success, novelty and engagement. Resumo. A inclusão da robótica para atividades acadêmicas já está bem estabelecida, com bons resultados em todo o mundo. No entanto, a robótica é realmente eficaz na pré-escola, especialmente quando as crianças têm uma interação duradoura com o robô? Este trabalho é focado no desenvolvimento de raciocı́nio lógico, cognitivo e matemático em crianças de 5 e 6 anos com o mesmo robô ao longo de um ano e meio. O objetivo é analisar se eles aprenderam o conteúdo abordado, e para entender quando e por que o aluno perde o interesse nas aulas. Os resultados mostraram que, para a interação de longo prazo, é necessário focar em quatro fatores: forma abordada, sucesso, novidade e engajamento.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121638015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"JogLog - Jogos de Raciocínio Lógico para Alunos do Ensino Fundamental: Um Estudo de Caso Utilizando Gamificação e Pensamento Computacional","authors":"O. Souza","doi":"10.5753/cbie.sbie.2019.1022","DOIUrl":"https://doi.org/10.5753/cbie.sbie.2019.1022","url":null,"abstract":"Studies demonstrate the importance of teaching computational thinking and programming logic in early school training due to its relevance in the development of problem solving in any area of knowledge. Thus, the teachinglearning process should be more attractive and encouraging, given the complexity of the contents. The aim of this study is to demonstrate the advantages of association of gamification with computational thinking in an extension course that uses logical reasoning games. The course was accomplished with elementary school students and used the tools Plastelina, Lightbot, Code.org and Scratch. The results show the effectiveness of the use of gamification associated with computational thinking in the teaching of programming logic in relation to the smoothing of the learning curve. Resumo. Estudos demonstram a importância do ensino do pensamento computacional e da lógica de programação na formação escolar o mais cedo possı́vel devido a sua relevância no desenvolvimento de resoluções de problemas em qualquer área do conhecimento. Sendo assim, o processo de ensinoaprendizagem deve ser mais atrativo e incentivador, dada a complexidade dos conteúdos. O objetivo deste estudo é demonstrar as vantagens da associação da gamification com o pensamento computacional em um curso de extensão que utiliza jogos de raciocı́nio lógico. O curso foi realizado com alunos do ensino fundamental e utilizou as ferramentas Plastelina, Lightbot, Code.org e Scratch. Os resultados obtidos evidenciam a efetividade do uso da gamification associada com o pensamento computacional no ensino de lógica de programação em relação à suavização da curva de aprendizagem.","PeriodicalId":290331,"journal":{"name":"Anais do XXX Simpósio Brasileiro de Informática na Educação (SBIE 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114592791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}