Filipe Dwan Pereira

Filipe Dwan Pereira
Universidade Federal de Roraima (UFRR) · Computer Science

About

56
Publications
4,411
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
268
Citations
Introduction
He holds a degree in Computer Science from the Federal University of Roraima (2010), MBA in Systems Engineering and a Master's Degree in Artificial Intelligence applied to Education from the Federal University of Amazonas. He has been a computer science professor of the Federal University of Roraima since 2013. Key research interests: data mining, predictive and prescriptive analytics, learning analysis, machine learning techniques, big data, and deep learning.
Additional affiliations
October 2013 - present
UFRR
Position
  • Professor (Assistant)
Description
  • Data Structure, Structured Programming, Object-Oriented Programming, Scientific Methodology for Computer Science, Low-level Programming, Computer Architecture and Organization, Operational Systems, Development for Mobile Devices, Database Management

Publications

Publications (56)
Article
Full-text available
There are many claims that gamification (i.e., using game elements outside games) impact decreases over time (i.e., the novelty effect). Most studies analyzing this effect focused on extrinsic game elements, while fictional and collaborative competition have been recently recommended. Additionally, to the best of our knowledge, no long-term researc...
Article
Full-text available
Students face several difficulties in introductory programming courses (CS1), often leading to high dropout rates, student demotivation, and lack of interest. The literature has indicated that the adequate use of gamification might improve learning in several domains, including CS1. However, the understanding of which (and how) factors influence ga...
Conference Paper
Full-text available
Um inventário de conceitos (IC) é um conjunto de questões de múltipla escolha ou discursivas com intuito de medir o conhecimento dos alunos em determinado tópico ou assunto. Visto que, no português brasileiro, não existe nenhum IC criado no tópico de programação introdutória, o objetivo principal desse trabalho visa traduzir e validar um inventário...
Conference Paper
Full-text available
This paper aims to replicate the study carried out by Lishinski et al (2016) that correlates the score of a Problem Solving questionnaire with the score obtained by the student at the end of the academic period of Computer Science 1 (CS1) course. To achieve the goal, the questionnaire was translated and validated, to be applied to the local context...
Conference Paper
Full-text available
Research seeks to understand the preferences of different user profiles in games and gamified environments. In this sense, this paper aims to identify and analyze the preferences and behaviors of users of different profiles within a gamification platform created around a multiplayer RPG game, developed and implemented in real introductory programmi...
Conference Paper
Full-text available
Plagiarism is a serious and growing problem in the academic environment, which interferes directly in the quality of teaching. This research is contextualized in the problem the detection of plagiarism in CS1 courses. In these courses, the codes developed by students tend to be simple and small, making it difficult for traditional methods based on...
Article
Full-text available
In introductory programming classes, online judges are used as a tool for preparing assessments through a random draw of programming questions. For the random draw of questions to be balanced, questions should be classified according to their difficulty or ease. Thus, this work presents two approaches to classify programming questions by using attr...
Article
Full-text available
Predicting student performance as early as possible and analysing to which extent initial student behaviour could lead to failure or success is critical in introductory programming (CS1) courses, for allowing prompt intervention in a move towards alleviating their high failure rate. However, in CS1 performance prediction, there is a serious lack of...
Conference Paper
Full-text available
Este estudo investiga como as vivências acadêmicas de estudantes de cursos de computação podem influenciar no desempenho dos alunos. A vivência acadêmica foi mensurada em 5 dimensões (Carreira, Pessoal, Institucional, Interpessoal, Estudo) utilizando o Questionário de Vivências Acadêmicas em sua versão reduzida (QVA-r) como um instrumento de previs...
Article
Full-text available
Apesar dos benefícios de uma via expressa de ônibus, o trabalho de engenharia para mapear quais vias devem compor a via expressa é complexo, já que existem exponenciais possibilidades de combinação. Note que computacionalmente falando, uma cidade pode ser vista como um grafo direcionado $G$ e uma via expressa pode ser representada por um subgrafo $...
Chapter
Full-text available
Programming online judges (POJs) are autograders that have been increasingly used in introductory programming courses (also known as CS1) since these systems provide instantaneous and accurate feedback for learners’ codes solutions and reduce instructors’ workload in evaluating the assignments. Nonetheless, learners typically struggle to find probl...
Chapter
Recently, the growing number of learners in Massive Open Online Course (MOOC) environments generate a vast amount of online comments via social interactions, general discussions, expressing feelings or asking for help. Concomitantly, learner dropout, at any time during MOOC courses, is very high, whilst the number of learners completing (completers...
Chapter
Although Massive Open Online Course (MOOC) systems have become more prevalent in recent years, associated student attrition rates are still a major drawback. In the past decade, many researchers have sought to explore the reasons behind learner attrition or lack of interest. A growing body of literature recognises the importance of the early predic...
Conference Paper
Full-text available
No ensino de programação, é comum o uso de Ambientes de Correção Automática de Código (ACACs). Esses apresentam uma alta diversidade de exercícios de programação que requerem que o estudante elabore um código como solução. Contudo, um obstáculo é classificar a facilidade ou dificuldade desses exercícios de modo que sejam apresentados conforme o nív...
Conference Paper
Full-text available
Alunos de disciplinas introdutórias de programação exibem vários entendimentos equivocados de conceitos e dificuldades no conhecimento sintático, conceitual e estratégico. Tais equívocos levam os alunos a cometerem erros como atribuições erradas em variáveis, chamadas de métodos não declarados, passagens erradas de parâmetros para métodos, dentre o...
Poster
Full-text available
The adoption of Online Judge (OJ) environments by CS1 instructors has increased over the last few years. A potential explanation of this growth is that OJs reduce instructors? workload in correcting learners? codes and provide instantaneous and accurate feedback to students about the correctness of their solutions. Despite the benefits, there are s...
Poster
Full-text available
Building predictive models to estimate the learner performance in the beginning of CS1 courses is essential in education to allow early interventions. However, the educational literature notes the lack of studies on early learner behaviours that can be effective or ineffective, that is, programming behaviours that potentially lead to success or fai...
Poster
Full-text available
Na Universidade Federal do Amazonas (UFAM), a disciplina de Introdução à Programação de Computadores (IPC) é ofertada como componente curricular obrigatório de 17 cursos de graduação non-major. Porém, a taxa de aprovação nessa disciplina, entre 2010 e 2019, oscilou entre 40% a 50%. Como uma forma de lidar com esse problema, este trabalho em progres...
Poster
Full-text available
O Instituto de Computação da Universidade Federal do Amazonas (UFAM) oferece a disciplina de Introdução à Programação de Computadores (IPC) para diversos cursos de áreas que não são de computação (conhecidos como non-CS majors), Os estudantes dos cursos non-CS majors podem enfrentar bastante dificuldade na disciplina, além de haver uma falta de int...
Poster
Full-text available
Um inventário de conceitos (IC) é um conjunto de questões, abertas ou de múltipla escolha, com o intuito de identificar as concepções errôneas (em inglês, misconceptions) dos alunos sobre determinado tópico ou curso. Apesar de ICs serem amplamente utilizados em algumas áreas do conhecimento, existem poucas propostas na área Computação. Mais especif...
Poster
Full-text available
Neste trabalho em progresso está sendo realizado um estudo sobre quais elementos de jogos mais motivam e atraem os diferentes tipos de usuários de sistemas gamificados, bem como quais são as tendências e interesses típicos dos usuários de cada tipo. O modelo HEXAD será adotado para classificar os usuários em seis tipos distintos. Para realizar esse...
Conference Paper
O Instituto de Computação da Universidade Federal do Amazonas (UFAM) oferece a disciplina de Introdução à Programação de Computadores (IPC) para diversos cursos de áreas que não são de computação (conhecidos como non-CS majors), Os estudantes dos cursos non-CS majors podem enfrentar bastante dificuldade na disciplina, além de haver uma falta de int...
Conference Paper
Building predictive models to estimate the learner performance in the beginning of CS1 courses is essential in education to allow early interventions. However, the educational literature notes the lack of studies on early learner behaviours that can be effective or ineffective, that is, programming behaviours that potentially lead to success or fai...
Conference Paper
Neste trabalho em progresso está sendo realizado um estudo sobre quais elementos de jogos mais motivam e atraem os diferentes tipos de usuários de sistemas gamificados, bem como quais são as tendências e interesses típicos dos usuários de cada tipo. O modelo HEXAD será adotado para classificar os usuários em seis tipos distintos. Para realizar esse...
Conference Paper
The adoption of Online Judge (OJ) environments by CS1 instructors has increased over the last few years. A potential explanation of this growth is that OJs reduce instructors? workload in correcting learners? codes and provide instantaneous and accurate feedback to students about the correctness of their solutions. Despite the benefits, there are s...
Conference Paper
Full-text available
Um inventário de conceitos (IC) é um conjunto de questões, abertas ou de múltipla escolha, com o intuito de identificar as concepções errôneas (em inglês, misconceptions) dos alunos sobre determinado tópico ou curso. Apesar de ICs serem amplamente utilizados em algumas áreas do conhecimento, existem poucas propostas na área Computação. Mais especif...
Conference Paper
Na Universidade Federal do Amazonas (UFAM), a disciplina de Introdução à Programação de Computadores (IPC) é ofertada como componente curricular obrigatório de 17 cursos de graduação non-major. Porém, a taxa de aprovação nessa disciplina, entre 2010 e 2019, oscilou entre 40% a 50%. Como uma forma de lidar com esse problema, este trabalho em progres...
Conference Paper
Full-text available
No ensino de programação utilizando juízes online, é importante apresentar ao estudante questões de programação em nível crescente de dificuldade, bem como equilibrar os níveis das questões sorteadas pelo ambiente durante avaliações. Este trabalho propõe e valida um método para classificar automaticamente a dificuldade de questões de programação co...
Conference Paper
Full-text available
Gamification design in educational environments is not trivial and many variables need to be considered to achieve positive outcomes. Often, educators and designers do not know when the students' intentions on the use of gamified environments might influence their experience. Based on this premise, this paper describes an exploratory study on the u...
Conference Paper
Full-text available
Typically, learners struggle to find suitable problems in online judges due to the huge volume of problems available on these systems. In this sense, we propose and validate methods for automatic recommendation of problems in online judges, where the recommendations are made based on a target problem, previously solved by the learner. In total, 15...
Conference Paper
Full-text available
The use of gamification in educational settings can have positive, neutral or even negative effects. Therefore, it is essential to assess the impact of gamification on student performance. Recent studies point to the use of analysis directed at student data to assess gamification instead of questionnaires that are poorly scalable and may present bi...
Conference Paper
Full-text available
Programming classes have a high failure rate and, as a result, many studies has been conducted to predict student performance, to help in decision making. The present work carried out a systematic mapping of studies from 2009 to 2019 to address six research questions. In total, we analysed 911 publications and filtered 70 works related to performan...
Conference Paper
Full-text available
Introduction to Programming (CS1) classes typically show high failure rates. Indeed, many studies have been carried out to understand how students develop code solutions and which behaviors may impact positively or negatively on their performance. In this sense, this study proposes and validates a model of state transitions in an Online Judge (OJ)...
Conference Paper
Full-text available
Apesar dos benefícios dos juízes online em relação ao processo de correção automática de códigos, a literatura afirma que o feedback desses sistemas precisa ser aprimorado para gerar um aprendizado mais efetivo para o estudante. Este artigo aprofunda um estudo anterior, do tipo intervenção-controle, e visa identificar se o feedback estendido aprese...
Conference Paper
Usuários regularmente apresentam dificuldades para encontrar problemas adequados em juízes online devido ao grande volume de exercícios disponíveis nesses sistemas. Nesse sentido, este estudo propõe e avalia três métodos para recomendação automática de problemas em juízes online, onde as recomendações são realizadas a partir de um problema alvo, re...
Article
Full-text available
Introductory programming may be complex for many students. Moreover, there is a high failure and dropout rate in these courses. A potential way to tackle this problem is to predict student performance at an early stage, as it facilitates human-AI collaboration towards prescriptive analytics, where the instructors/monitors will be told how to interv...
Preprint
Full-text available
While Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback. Several features are considered to contribute towards learner attrition or lack of interest, which may lead to disengagement or total dropout. The jury is still out on which factors are the most a...
Conference Paper
Full-text available
As programming must be learned by doing, introductory programming course learners need to solve many problems, e.g., on systems such as 'Online Judges'. However, as such courses are often compulsory for non-Computer Science (non-CS) undergraduates, this may cause difficulties to learners that do not have the typical intrinsic motivation for program...
Chapter
Identifying users’ demographic characteristics is called Author Profiling task (AP), which is a useful task in providing a robust automatic prediction for different social user aspects, and subsequently supporting decision making on massive information systems. For example, in MOOCs, it used to provide personalised recommendation systems for learne...
Chapter
The impact of gamification has been typically evaluated via self-report assessments (questionnaires, surveys, etc.). In this work, we analise the use of gamification elements as parameters, to predict whether students are going to fail or not in a programming course. Additionally, unlike prior research, we verify how usage of gamification features...
Article
Tools for automatic grading programming assignments, also known as Online Judges, have been widely used to support computer science (CS) courses. Nevertheless, few studies have used these tools to acquire and analyse interaction data to better understand the students’ performance and behaviours, often due to data availability or inadequate granular...
Thesis
Full-text available
Online judges are platforms used by many users who wish to improve their programming knowledge, as these systems provide immediate feedback to the user on the outcome of their submission. However, because the categorization of problems on online judges is done manually, the problems laid out on these systems may not be categorized or inappropriatel...
Thesis
Full-text available
Users from online judges often struggle to solve some problems because the problems might beunfitted to their programming knowledge. Note that it is important for online judges have manyproblems available, however this bring about an overload of information for users. Literature haspresented many relevant results for this problem of information ove...
Thesis
Full-text available
Studies indicate that the Brazilian population is close to 209 million inhabitants and one of the problems faced is the increase in the number of vehicles that causes the increase of pollution, traffic jam and long waits for public transportation. This makes it an unattractive option in the eyes of consumers. Public transport is a fundamental servi...
Conference Paper
Full-text available
In this work, we present an approach to predict student performance in the very first two weeks from CS1 classes, which use programming online judges. We performed the prediction with a binary classification, i.e., we estimated whether the student succeeded or failed. To do so, we employed a method using an evolutionary algorithm to build and optim...
Conference Paper
Full-text available
The objective of this work is to evaluate the generalizability of a method for predicting the performance of CS1 students in an online judge. To achieve this goal, we present an adaptation of the method to a dataset generated through a educational context different from the one in which the method was originally evaluated. As a result, we observed...
Poster
Full-text available
Many researchers have started extracting student behaviour by cleaning data collected from web environments and using it as features in machine learning (ML) models. Using log data collected from an online judge, we have compiled a set of successful features correlated with the student grade and applying them on a database representing 486 CS1 stud...
Article
Full-text available
This paper shows a comparative study of machine learning techniques to recognize emotions in images through the characterization of facial expressions. Well-Reputed research shows that human beings emotions could be characterized using a Facial Action Coding System (FACS), which is a taxonomy to classify the human being facial expressions. The same...
Chapter
Full-text available
Many educational institutions have been using online judges in programming classes, amongst others, to provide faster feedback for students and to reduce the teacher’s workload. There is some evidence that online judges also help in reducing dropout. Nevertheless, there is still a high level of dropout noticeable in introductory programming classes...
Chapter
Full-text available
While Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback. Several features are considered to contribute towards learner attrition or lack of interest, which may lead to disengagement or total dropout. The jury is still out on which factors are the most a...
Thesis
Full-text available
Muitas instituições de ensino superior vêm utilizando Juízes Online em turmas de Introdução à Programação de Computadores (IPC) para que haja um feedback mais rápido para os alunos e para diminuir a carga de trabalho do professor. Entretanto, mesmo com o uso dessa estratégia ainda existe um alto índice de evasão nas turmas de IPC. Neste sentido, mu...
Thesis
Full-text available
Researchers from different areas has an interest in emotions, even if their focus are distinct this subject has a direct impact in the behavior and coexistence of human beings. Paul Ekman discovered the existence of six universal emotions: happiness; sadness; fear; disgust; anger; and surprise. Based on this study, Paul Ekman developed a Facial Act...

Network

Cited By

Projects

Projects (4)
Project
Increasing students' outcomes by using learning analytics tools; Providing methods and tools to support the learning process. Providing decisions options to educational stakeholders;