ResumoUm dos desafios para as instituições de ensino superior é obter métricas que auxiliem o acompanhamento do desempenho do discente tendo em vista as constantes transformações do ensino no país. A mineração de dados vem sendo uma das principais ferramentas utilizadas por conseguir extrair informação implícita, previamente desconhecida e potencialmente útil para tomada de decisão. Neste trabalho foi analisada uma base de dados de estudantes do curso de Engenharia de Computação da Universidade Federal do Rio Grande (FURG), onde houve uma mudança na forma de avaliação para o ingresso dos alunos no ensino superior. Foram gerados modelos para avaliar o impacto desta alteração os quais mostram que o desempenho dos alunos diminuiu. Utilizando modelos de dados preditivos, percebeu-se que a idade, as notas de ingresso e o número de repetições nas disciplinas são fatores preponderantes para que aluno conclua o curso.Palavras-chave: Mineração de dados, Classificação, Regressão.
AbstractOne of the challenges for higher education institutions is to obtain metrics that help monitor students' performance in view of the constant transformations of teaching in the country. Data mining has been one of the main tools used to extract implicit, previously unknown and potentially useful information for decision making. In this work, a database of students of the Computer Engineering course of the Universidade Federal do Rio Grande (FURG) was analyzed, where there was a change in the form of evaluation for students' admission to higher education. Models have been generated to assess the impact of this change which show that student performance has declined. Using predictive data models, it was noticed that the age, the grades of entry and the number of repetitions in the disciplines are preponderant factors for the student to complete the undergraduate course.
Abstract. The increase of the Internet access and the popularity of mobile devices have influenced the consumption of radio/TV programs on the Web. An alternative for customization programming is the use of recommendation systems to adapt the content transmitted based on the preference of the listeners. The behavior of users accessing content on the Web is highly uncertain and naturally diffuse. In this paper, we propose an approach based on fuzzy set theory to analyze the similarity between users of Web radio programs, capturing similar interests from streaming data available in log files.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.