Jorge Luis Cavalcanti Ramos

Discovering Level of Participation in MOOCs through Clusters Analysis

This paper presents an analysis using hierarchical grouping method (ward grouping) and the non-hierarchical grouping method (k-means) to analyze the participation levels in activities and interactions in a virtual forum. Data came from a MOOC and it was on grammatical rules of Brazilian Portuguese. About 5100 participants integrated the course. It lasted about three months and the activities developed by means of the Openredu learning platform. We analyzed data of collaboration, interaction, and discussions in forums, access data and activity on the Openredu. The results pointed to three distinct engagement strategies. Those categories oriented the proposition of an interface design guidelines for MOOC to conceive adaptive strategies that permit to increase engagement and favor an improved learning experience.

A Comparative Study between Clustering Methods in Educational Data Mining

This paper aims to describe the analysis of data from the Moodles database of a beginner class in Distance Education of a Federal University using distinct educational data mining clustering methods. We carried out clustering using hierarchical and non-hierarchical methods in different groups of students, according to their interaction and performance characteristics. In the analysis, it was possible to perceive the groups obtained, a similarity between the results of each method used, confirming the acquired knowledge from the clustering and demonstrating that the choice of method in this study had little influence on the knowledge obtained from interactions and students performance on the course.

Uma abordagem preditiva da evasão na educação a distância a partir dos construtos da distância transacional

The growth of Distance Education (DE) has been supported by theories to aid in the planning and execution of courses in an effective and efficient way. Research in this area also reflects this growth, as they seek to mitigate or solve problems arising from this expansion, such as the high rates of dropouts still observed in the modality. For most of the institutions that participated in the DE Annual Census in Brazil in 2015, the greatest obstacle has been the avoidance of courses, when for 40% of the institutions surveyed, the average rate of dropout was between 26% and 50% in courses offered at a distance by these institutions. Based on a need to renew DE theories, as well as applying them to help addressing the challenges of the modality, this research focused on the Transactional Distance Theory proposed by Moore (1972, 1973, 1993, 2013). It was suggested a new approach to determine their constructs, with the purpose of applying them in a process of early detection of students with tendencies to dropout, in higher distance courses. The use of multivariate analysis techniques to obtain the transactional distance constructs, had the intention of looking for a different approach than those currently found in the literature. This determination is made, in most cases, using questionnaires applied to students and teachers. In addition, the literature evidences the use of several techniques of data mining and machine learning in the definition of predictive models in educational contexts, with satisfactory indexes of precision. After obtaining the components (variables) of the constructs, it was also defined and validated a model of prediction of the dropout students in distance courses, from these components. Several classifiers algorithms were used, and the logistic regression classifier presented more relevant results when compared to those recorded in the literature. Since then, an application with the predictive model was implemented for test with users and was been well accepted by teachers and tutors who work with DE.

Ciência de Dados Educacionais: definições e convergências entre as áreas de pesquisa

The growing interest in the application of Big Data-based techniques in problems belonging to the context of Computers in Education stimulated the emergence of research initiatives, gathered under different names: Educational Data Mining, Learning Analytics and, more recently, Academic Analytics. Considering the existence of several common points between these areas and also a certain lack of definition about the boundaries between them, this article intends to contribute to a greater conceptual clarity in this field, when adopting the term Educational Data Science to broadly analyze the main topics covered for the articles of six national and international events dedicated to the subject. Resumo. O crescente interesse na aplicação de técnicas oriundas da área de Big Data em problemas pertencentes ao contexto da Informática na Educação estimulou o surgimento de pesquisas reunidas sob diferentes nomes: Mineração de Dados Educacionais, Analíticas de Aprendizagem e, mais recentemente, Analíticas Acadêmicas. Considerando os diversos pontos em comum entre essas áreas e também uma certa indefinição da fronteira entre elas, este artigo pretende contribuir para uma maior clareza conceitual nesse campo, ao adotar o termo Ciência de Dados Educacionais para analisar, de maneira ampla, os principais tópicos trabalhados pelos artigos de seis eventos nacionais e internacionais dedicados ao tema. 1. Introdução Com o crescimento exponencial da geração de dados por usuários, dispositivos e sistemas, as tecnologias associadas ao Big Data apresentam-se como novas oportunidades para análise, entendimento, modelagem e predição de diversas variáveis presentes em grande volume de dados. Assim como nas demais áreas afetadas pelo Big Data, o campo educacional vem incorporando cenários dessas tecnologias, em virtude das diversas abordagens DOI: 10.5753/cbie.wcbie.2017.764 764 Anais dos Workshops do VI Congresso Brasileiro de Informática na Educação (WCBIE 2017) VI Congresso Brasileiro de Informática na Educação (CBIE 2017)

Mineração de Dados Educacionais Orientada por Atividades de Aprendizagem

Este trabalho, por meio de um estudo de caso, apresenta uma abordagem de Mineracao de Dados Educacionais orientada por atividades de aprendizagem, tendo como referencia a Teoria da Atividade. O objetivo do estudo foi analisar as diferencas nos resultados dessa abordagem em relacao a um processo de mineracao holistico, no qual os modelos de predicao permitem analises apenas no nivel de disciplina, sem a observacao de detalhes das atividades de aprendizagem. Os resultados desta pesquisa apontam vantagens da mineracao orientada por atividade, que oferece informacoes em um contexto de interacao significativa, com mais subsidios para monitorar e tratar contradicoes no processo de aprendizagem.

Mapeamento Sistemático sobre Abordagens de Mensuração de Autorregulação da Aprendizagem

Este trabalho teve como objetivo o desenvolvimento de um mapeamento sistematico com a finalidade de identificar as principais abordagens de mensuracao de caracteristicas de autorregulacao da aprendizagem em ambientes online. A identificacao destas abordagens fornecem subsidios para identificar as principais formas de analises e coletas que estao sendo utilizadas na literatura. Os resultados mostram que ainda e pouca expressiva a quantidade de trabalhos que utilizam dados comportamentais, atraves de logs, para a mensuracao em tempo real. Este parece ser um tema desafiador especialmente considerando o numero cada vez maior de cursos a distância, numero de alunos e volume de dados gerados em plataformas de aprendizagem online.

Validação de um instrumento de mensuração de autorregulação da aprendizagem em contexto brasileiro usando análise fatorial confirmatória

A escala de autorregulacao da aprendizagem Online Self-Regulated Learning Questionnaire (OSLQ), desenvolvida por (Barnard, Lan e To, et al. 2009), e um instrumento para avaliar as caracteristicas de autorregulacao da aprendizagem de estudantes em cursos na modalidade online. O presente estudo visa investigar a aplicabilidade deste instrumento, verificando se o mesmo e valido para mensurar caracteristicas de autorregulacao da aprendizagem nos moldes da educacao a distância no Brasil. Foi realizada uma pesquisa com 408 participantes de cursos na modalidade EAD com idade media de 30 anos (DP=18,23). A analise dos dados foi realizada por meio de analise fatorial confirmatoria e os resultados indicaram que o modelo de seis fatores mensurado atraves dos itens do instrumento se ajusta a amostra analisada no Brasil. Consideracoes acerca da validade interna e da proposta conceitual do instrumento sao discutidas neste artigo.

Discovery engagement patterns MOOCs through cluster analysis

Cluster analysis can be used to help researchers identify behavioral patterns of students with regard to engaging in interactions via the forum and during activities during a course in MOOC mode (English, Massive Open Online Course). This article aims to analyze the effectiveness of educational data mining techniques, specifically the cluster analysis to identify students engagement patterns in MOOC courses in mode. The analyzes in this article demonstrate the use of hierarchical clustering method (Ward clustering) and the non-hierarchical clustering method (k-means) to analyze the engagement behavior characteristics, involving carrying out activities and interactions via the forum. For the analysis were taken into account the interaction patterns made in discussion murals in Openredu platform, as well as data access and activities of completeness. The insights found in this study can serve as indications for use by MOOCs designers to meet the diversity of engagement patterns and design interfaces that guide the design of adaptive strategies that allow increasing engagement and fostering a better learning experience.

Analysis of students' expectations and skills in e-learning

This study aims to identify evidence of variation levels of expectations and skills of beginners students in an undergraduate course in e-learning. From the questionnaires at the beginning and in the end of a discipline of course and after statistical graphics for treatment of data, the results showed that expectations of students to start the course in the e-learning were changed significantly during the same. Another important factor was perception of change in skills acquired during the course, as it may also indicate an increase in self-confidence and motivation of the students to continue their studies. Specific issues such as: available material, interaction with colleagues, resources of the virtual environment and the presentation of content by teachers. All of them were also evaluated in two moments of the discipline and it showed satisfactory results for planning the course.