Mestrado em Ciência da Computação (INF)

URI Permanente para esta coleção

http://200.137.215.59/tede/handle/tde/225

Navegar

Navegando Mestrado em Ciência da Computação (INF) por Por Orientador "Ambrósio, Ana Paula Laboissière"

Agora exibindo 1 - 4 de 4
  • Nenhuma Miniatura disponível
    Item
    Juiz online no ensino de CS1: requisitos, dificuldade de problemas e plágio em código-fonte
    (Universidade Federal de Goiás, 2016-08-30) Francisco, Rodrigo Elias; Ambrósio, Ana Paula Laboissière; http://lattes.cnpq.br/0900834483461062; Ambrósio, Ana Paula Laboissière; Longo, Humberto José; Matos, Fernando Barbosa
    This dissertation approaches Online Judge in teaching Introductory Programming (CS1). Initially there was an exploratory research on BOCA system in teaching CS1, which brought experiences and data of student interactions with the system, which, supported by Systematic Literature Review (RSL), contributed to defining the requirements for the system meets the discipline of CS1 and guided continuing research. In the second phase, there was the aim to solve specific problems identified in the previous phase, and measuring the difficulty of CS1 problems and support for plagiarism identification in CS1 activities. The solution of these problems included RSL, practical experiences with writing and execution algorithms, comparison of the results with the expected results, and comparison of the proposed approaches to the identified in the literature. The strategy to measure the difficulty of problems CS1 proposed works with the height of a tree mounted to sets and sub-sets of nested code into a program and the amount of related subjects. The strategy to support the identification of plagiarism proposal works with the Edit Distance algorithm processing and normalization techniques in preprocessing, and it is a highly adapted proposal to the reality of the data used in this research (programs written in C with few lines of code by students CS1). Experience has shown the complexity of applying computing to education, which often works with subjective data, it was necessary to raise the difficulty of the problems in view of the students and the teacher’s view of the existence of plagiarism in peer programs, whose views are quite variables. It is suggested the creation of multidisciplinary teams to the evolution of the area (with professionals of computing, statistics, psychology and pedagogy) with a focus on validation and method used for research.
  • Nenhuma Miniatura disponível
    Item
    Estudo exploratório do uso de classificadores para a predição de desempenho e abandono em universidade
    (Universidade Federal de Goiás, 2016-10-20) Motta, Porthos Ribeiro de Albuquerque; Albuquerque, Eduardo Simões de; http://lattes.cnpq.br/8181318469884254; Ambrósio, Ana Paula Laboissière; http://lattes.cnpq.br/0900834483461062; Ambrósio, Ana Paula Laboissière; http://lattes.cnpq.br/0900834483461062; Soares, Anderson da Silva; Almeida, Leandro da Silva
    Educational Data Mining, by the triad of quality improvement, cost reduction and educational effectiveness, acts and seeks to better understand the teaching and learning process. In this context, the aim of this work is an exploratory study of classification methods to predict student performance and dropout from data in university academic databases. In this study we used demographic, socio-economic and academic results, obtained from the Vestibular and the university database to analyze several classification techniques, as well as balancing and attribute selection techniques, identified through a systematic review of the literature. Following a trend found in the selected articles, we chose to use decision trees as the primary classification algorithm, although comparative studies showed better results with logistic regression techniques and Bayesian networks. This is because decision trees allow an analysis of the attributes used in the generated models while maintaining acceptable levels of accuracy, while other techniques work as a black box. Through the tests we found that you get better results using balanced sets. In this sense, the Resample technique that selects a balanced subset of the data showed better results than SMOTE technique that generates synthetic data for balancing the dataset. Regarding the use of attribute selection techniques, these did not bring significant advantages. Among the attributes used, grades and economic factors often appear as nodes in the generated models. An attempt to predict performance for each subject based on data from previous courses was less successful, maybe because of the use of ternary predictive classes. Nevertheless, the analysis carried out showed that the use of classifiers is a promising way to predict performance and dropout, but further studies are still needed.
  • Nenhuma Miniatura disponível
    Item
    Explorando a tinta digital para a avaliação: análise de traços simples
    (Universidade Federal de Goiás, 2015-10-13) Pereira Júnior, Cleon Xavier; Ambrósio, Ana Paula Laboissière; http://lattes.cnpq.br/0900834483461062; Ambrósio, Ana Paula Laboissière; Ferreira, Deller James; Macedo, Joaquim Melo Henrique
    Digital ink technology is available in several electronic devices and can bring contributions to the evaluation process as it allows access to information that was not available in assessments carried out using traditional methods. It is particularly interesting in evaluations involving drawings, since it offers an environment quite similar to pencil and paper, with the advantage of allowing process automation. Thus, the first step is to provide resources to capture, store and reproduce the design done. Then, it is necessary to analyze the collected data. However, analysis of drawings is a complex task and focus of several research projects. Thus, as an initial contribution, this work focuses on the analysis of simple traces. In order to explore digital ink as a means of evaluation, a tool was developed to automate the capture, storage and reproduction of drawings, and test the features and limitations of the analysis of digital ink in order to extract relevant knowledge for the evaluator to make decisions. To test the tool, psychological tests were selected, since in this knowledge domain the use of drawings for assessment is widespread. The tool was developed in two stages. The first, more general, offers resources for test application, storage and later playback for an analysis by the evaluator, not providing resources for automatic analysis of results. Though simple, these resources offer a great contribution, because in addition to storing the final result, which can be visualized as an image, it also stores the design process (allowing the evaluator to follow step by step how the test was performed) in addition to storing other information such as time spent to perform certain steps, the use of rubber etc. The second stage of the tool is the analysis of the stored data. This analysis is test dependent, and should be implemented according to it’s evaluation requirements. As a case study, a test, that uses simple traces, was implemented. The result showed that the digital ink has advantages for carrying out evaluations using drawings as a medium, and should be subject to further research aimed at automating tests with more complex drawings.
  • Nenhuma Miniatura disponível
    Item
    Predição de desempenho no Moodle usando princípios da andragogia
    (Universidade Federal de Goiás, 2020-05-15) Trindade, Fernando Ribeiro; Ferreira, Deller James; http://lattes.cnpq.br/1646629818203057; Ambrósio, Ana Paula Laboissière; http://lattes.cnpq.br/0900834483461062; Rodrigues, Cássio; Siqueira, Sean Wolfgand Matsui; Ferreira, Deller James
    According to current literature, the teaching skills of tutors are essential to ensure excellence in teaching and, consequently, the interest of students in courses. In online teaching environments, students and tutors interact with each other through the various communication resources provided by virtual learning environments (VLE). With this, a large amount of educational data is collected by AVAS’s, making it possible to carry out analyzes of these data. However, in the academic literature, few studies have been conducted in order to collect behavioral data from tutors and use this data to make the prediction of students' school performance. Therefore, in this dissertation a framework of tutoring characteristics was elaborated correlated to the good school performance of students, and this framework was used to guide the data collection of tutors, which were used to make the prediction of student performance. The tutoring characteristics included in the framework were extracted from previous research, which investigated each tutoring attribute, and from tutoring attributes desired by Andragogy. The prediction of students' performance was carried out from the development of an extension of the Moodle Predicta tool, which performs classification of students as to possible failure or approval. The prediction of student performance is made from the behavioral data of students and tutors. The implementation of the prediction was preceded by a performance analysis of the classifying algorithms, and the implemented classifier was RandomForest, which achieved better performance according to the AUC metric. Educational data from Moodle from the Goiás Judicial School (EJUG) was used in a case study. Two exploratory data analyzes were conducted to learn about the courses and investigate the tutoring characteristics of the framework in EJUG tutors. The data from EJUG tutors were included in the classification model, used to predict student performance, showing that the actions of tutors can impact students' academic achievements.