Fernanda Campos

Universidade Federal de Juiz de Fora

Student dropout from higher education is still a challenge, imposing a financial and human burden and refusing students to learn. Brazil witnessed a university dropout rate of almost 55%. This work aims to analyze the factors that lead to student dropout from Information System courses, exploring the profile of students, using intelligent technique...

The educational domain comprises fragmented solutions with different services, tools, and plugins. As a complex system, it raises several security and threat prevention concerns. We conducted an exploratory study to characterize security vulnerabilities and their impacts on Learning Management Systems. We focus on an intelligent educational solutio...

The software development industry has evolved in recent years, presenting new challenges. In this scenario, software ecosystems have emerged as a new development paradigm through which external contributors support software production by providing solutions that complement a common ecosystem platform. Due to the many technologies, frameworks, and d...

Massive Open Online Courses (MOOCs) are a teaching method that uses Virtual Learning Environments to reach a vast number of students, thus, facilitating access to education by making costs more appealing because of scale economics. Consequently, Tutors’ and teachers’ interaction is crucial for the successful development of a MOOC. However, due to t...

Accompanying students in virtual learning environments to identify those who need help is a difficult and time-consuming task. Identifying subjective attributes that recognize students’ feelings can help teachers and tutors in pedagogical interventions. The interaction must motivate and keep students engaged. This article proposes an architecture c...

Educational institutions are moving to a hybrid model that allows onsite and online classes. Students and teachers must adapt to these changes in the teaching and learning routine, leading them to stress and anxiety moments. This work proposes an architecture to assist academics in detecting these stressful moments during daily activities. The prop...

In scientific collaboration, data sharing, the exchange of ideas and results are essential to knowledge construction and the development of science. Hence, we must guarantee interoperability, privacy, traceability (reinforcing transparency), and trust. Provenance has been widely recognized for providing a history of the steps taken in scientific ex...

In social network analysis, a key issue is the detection of meaningful communities. This problem consists of finding groups of people who are both connected and semantically aligned. In the software development context, identifying communities considering both collaborations between developers and their skills can help to address critical elements...

Provenance is recognized as a central challenge to establish the reliability and provide security in computational systems. In scientific workflows, provenance is considered essential to support experiments’ reproducibility, interpretation of results, and problem diagnosis. We consider that these requirements can also be used in new application dom...

Massive Open Online Courses (MOOCs) make up a teaching modality that aims to reach a large number of students using Virtual Learning Environments. In these courses, the intervention of tutors and teachers is essential to support students in the teaching-learning process, answer questions about their content, and provide engagement for students. How...

Massive Open Online Courses (MOOCs) make up a teaching modality that aims to reach a large number of students using Virtual Learning Environments. In these courses, the intervention of tutors and teachers is essential to support students in the teaching-learning process, answer questions about their content, and provide engagement for students. How...

Dropping out of school comes from a long-term disengagement process with social and economic consequences. Being able to predict students' behavior earlier can minimize their failures and disengagement. This article presents the SASys architecture, based on a lexical approach and a polarized frame network. Its main goal is to define the author's se...

Monitoring students in virtual learning environments can be a time-consuming task. Professors and tutors must accompany students in an agile manner. During the COVID-19 pandemic, the use of discussion forums posed new challenges. This work proposes a conversational agent to automatically detect which pedagogical intervention is necessary to guide s...

A evasão escolar é um verdadeiro desafio para os especialistas em educação. Os cursos de educação a distância lidam com o desengajamento e abandono dos alunos, que resulta em impactos sociais e econômicos. Fatores comportamentais, cognitivos e demográficos podem estar associados à evasão escolar precoce. Este artigo propõe uma arquitetura baseada e...

Este trabalho apresenta algumas perspectivas relacionadas ao pensamento computacional no ensino médio. O trabalho apresenta o conceito de pensamento computacional, enfatizando sua eficácia e suas formas de aplicação como uma forma de auxiliar o processo de aprendizagem no ensino médio. São apresentadas as dificuldades enfrentadas durante o desenvol...

The increased demand for food worldwide, the reduced land availability for livestock production, the increasing cost of animal feed and the need for mitigating livestock-related greenhouse gas emissions have driven the search for animal feeding systems that proves more efficient. To tackle this problem, we propose the use of computational support t...

Finding developers to assist with project issues is essential in Global Software Development (GSD) contexts, where various individuals with distinct characteristics are involved. Several recommending approaches lead to identifying the same group of individuals who end up work overloaded. Aiming to diversify the recommendation process, we introduced...

This research presents a comprehensive methodological approach to detect and analyze student engagement within the context of online education. It is supported by e-learning systems, and is based on a combination of semantic analysis, applied to the students’ posts and comments, with a machine learning-based classification, performed upon a range o...

Patient follow-up appointments are an imperative part of the healthcare model to ensure safe patient recovery and proper course of treatment. The use of mobile devices can help patient monitoring and predictive approaches can provide computational support to identify deteriorating cases. Aiming to aggregate the data produced by those devices with t...

Dropping out of school is a real challenge for educational specialists. Distance education classes deal with a huge number of students’ disengagement with social and economic costs. Behavioral, cognitive, and demographic factors may be associated with early school dropout. This paper proposes an enhanced machine learning ensemble predictive archite...

SECon Ontology model in DL semantics

A systematic mapping seeks to answer questions through a literature review, following a review protocol that guarantees a higher level of reproducibility of the results. Following the guidelines of KITCHENHAM (2004) to define a mapping protocol, first the mapping objective must be specified, so that the research questions can be outlined. The objec...

With increasingly complex activities, scientific workflows are becoming more data-intensive. In this context, may require a collaborative, distributed or high performance (HPC) environment such as grids or clouds for their execution. Considering its extensibility feature, resources pool and pay-to-use, cloud computing environments have been increas...

Safety-critical Product Lines are required to demonstrate compliance with domain-specific safety standards. Different component configurations may require the inclusion or exclusion of certain features depending on their impact on safety. Additionally, variants may present distinct criticality levels which imply in different safety requirements dur...

Coletar informações de redes sociais se tornou essencial para a sobrevivência e modernização de muitas empresas. Com este objetivo, este trabalho apresenta uma arquitetura capaz de buscar, analisar e recomendar o conteúdo e a propagação de informações nas redes sociais, considerando o mercado de laticínios brasileiro. Usando ontologias e mecanismos...

Many application domains need to recommend resources for users. The development of solutions focused on the reuse of Recommender System components creates an interesting scenario from a Software Ecosystem perspective. Besides the interaction between actors and technology, a Software Ecosystem for the development of Recommender Systems should allow...

A capacidade de ecossistemas de software de evoluírem por colaboradores possibilita a criação de um ambiente que possa atender às necessidades de colaboração específicas de cada equipe. Entretanto, desenvolver novos serviços para um ecossistema pode ser uma tarefa difícil. Este trabalho propõe um processo para o desenvolvimento de serviços de colab...

Smart city environments, when applied to healthcare, improve the quality of people’s lives, enabling, for instance, disease prediction and treatment monitoring. In medical settings, case prioritization is of great importance, with beneficial outcomes both in terms of patient health and physicians’ daily work. Recommender systems are an alternative...

The Internet of Things (IoT) is a technological paradigm which aims to connect, in a global network, several devices and intelligent machines capable of exchanging information with each other. IoT purpose will only be achieved when the entities present in this network can fully interoperate with each other. However, the heterogeneity of devices, an...

In scientific collaboration, the data sharing, the exchange of ideas and results is crucial to promote knowledge and accelerate the development of science. Trust is extremely important in this context as well as reproducibility. Although in scientific workflow the provenance has been the basis for reproducibility, in collaborative environments it i...

In scientific collaboration, the data sharing, the exchange of ideas and results is crucial to promote knowledge and accelerate the development of science. Trust is extremely important in this context as well as reproducibility. Although in scientific workflow the provenance has been the basis for reproducibility, in collaborative environments it i...

Recommender Systems (RS) seek to present resources with features that meet users' interest and needs. The use of these systems with social networks, which have characteristics of information propagation and sharing, enables the dissemination of recommended resources. In order to study and identify the information diffusion metrics that are most rel...

There are several educational resources distributed in different repositories that address to a wide range of subjects and different educational goals. The proper choice of these educational resources is a challenge. Recommendation systems may help users in this task. In order to generate personalized recommendations, it is important to identify in...

In social network analysis, the detection of communities—composed of people with common interests—is a classical problem. Moreover, people can somehow influence any other in the community, i.e., they can spread information among them. In this paper, two models are proposed considering information diffusion strategies and the identification of commu...

This article describes the evolution of the PERSONNA ontology for modeling the student profile and contextin an e-learning environment, creating the PERSONNA-TEC ontology and its integration into the BROAD-RS architecture. This system is able to perform the recommendation of context-sensitive learning objects(LO), and enrich, flexibilize and dynami...

The global open source software development popularity motivates the search for experts with capability of helping other developers in solving complex tasks. The challenge is: given a task, how to identify an expert (or set of experts) to execute it? This problem is named the expert-location problem. Some of these search difficulties are the large...

Este trabalho discute algumas características de um ecossistema de software científico e do ciclo de vida de um experimento, com ênfase em manutenção e evolução dos experimentos, usando dados de proveniência. Uma extensão do modelo PROV é apresentada conjuntamente com uma ontologia, PROV-OEXT. O artigo também apresenta repositórios de workflows exi...

A FrameNet Brasil é um projeto de lexicografia computacional que tem como objetivo usar frames para a descrição de significados de palavras. Ela gera uma rede de frames que se ligam com relacionamentos específicos. O processo de criação ou atualização de um frame pode passar por mais de um especialista da Linguística, em momentos diferentes, o que...

Social network communities are composed of people with common interests who influence or are influenced by themselves. In the scientific context, Scientific Social Networks are characterized as social networks that represent the social relations established by researchers. Identifying and exploring these relationships are fundamental activities to...

We present BROAD-PLG, a Software Product Line to support the construction of educational games, with a set of features that will integrate the artefact to be developed. The evaluation was based on the development of the infrastructure and the generation of new products. It followed two steps: the development of a game for teaching Logic using the d...

The need to recommend resources in many different application domains and to develop solutions focused on recommender systems (RS) components reuse create an interesting scenario for the adoption of Software Ecosystem (SECO) perspective. In this way, the problem addressed by this study is how to integrate the various methods of existing recommendat...

This paper presents a solution based on analyses of complex networks in order to address context alignment and context loss between researchers working in projects and possibly in scientific experiments. Network edges with weights indicate the level of alignment between the researchers’ contexts. The analyses showed that the context mismatch betwee...

O cenário da tecnologia disponível atualmente favorece cada vez mais a criação de componentes para apoiar a construção de ferramentas para apoiar o ensino e a aprendizagem. Tais componentes são frequentemente denominados de Objetos de Aprendizagem (OAs). Entretanto, a construção de OAs torna-se cada vez mais complexa considerando-se as necessidades...

Learning objects are any resources that may assist in the process of teaching and learning to be reused in different contexts. However, when considering the reuse of content, the need to adapt to the student profile is also noted. Therefore, this paper presents BROAD-RS architecture which was designed in order to perform context-sensitive recommend...

Providing historical information to deal with knowledge loss about a scientific experiment has been the focus of some several researches. However, computational support for large-scale scientific experiments is still incipient and is considered one of e-science's greatest challenges. In this vein, providing provenance information to a scientist is...

[Context] Significant changes are occurring in the scientific scenario. In particular, there is increasing collaboration among researchers, which has led to the increasing use of processing techniques and the need to share results and observations. Researchers usually need to compose experiments using available services to fulfill their requirement...

Com mercado atual cada vez mais competitivo, produtores leiteiros precisam reduzir custos e tornar seus rebanhos competitivos. Nesse sentido, o apoio computacional vem fornecendo alternativas a identificação de animais mais eficientes e, por consequência, proporcionando ganhos econômicos e ambientais. Este artigo apresenta uma arquitetura para apoi...

Comunidades em redes sociais são compostas por pessoas com interesses comuns, que influenciam ou são influenciadas por elas mesmas. Neste trabalho são aplicados conceitos de análise de redes complexas para verificar o nível de influência entre os pesquisadores, analisando a estrutura da rede social científica e suas comunidades. São propostos um mo...

Test case prioritization (TCP) techniques aim to reorder test cases execution according to a goal. One common goal is fault detection, in which test cases that have a higher chance of detecting a fault are executed first than the remaining test cases. The goal of this study is to investigate TCP empirical studies in order to synthesize reported eff...

Regression tests are executed after every change in software. In a software development environment that adopts Continuous Software Engineering practices such as Continuous Integration, Continuous Delivery and Continuous Deployment, software is changed, built and tested many times. Every regression test execution may include different situations an...

Redes Sociais permitem detectar relações entre pessoas em ambientes colaborativos. A análise dessas relações surge como um importante mecanismo para potencializar a colaboração entre os grupos de pesquisa, através da criação de serviços, visando apoiar a realização de experimentos científicos. No contexto de um Ecossistema de Software Científico, é...

Managing contextual and provenance information plays a key role in the scientific domain. Activities which are carried out in this domain are often collaborative and distributed. Thus, aiming to examine and audit results already obtained, researchers need to be aware of the actions taken by other members of the group. Contextual and provenance info...

A scientific software ecosystem aims to integrate all stages of an experiment and its related workflows, in order to solve complex problems. In this vein, in order to assure the experiment proper execution, any modification that occurs must be propagated to the associated workflows, which must be maintained and evolved for the successful conduction...

Data provenance is a fundamental concept in scientific experimentation. However, for their proper understanding and use, efficient and user-friendly mechanisms are needed. Research in software visualization, ontologies and complex networks can help in this process. This paper presents a framework to assist in the understanding and use of data prove...

Esse artigo descreve uma arquitetura aberta para sistemas de recomendação, com etapas, aspectos de perfil e contexto, técnicas e métodos, que pode ser adaptada a diversos domínios. Essa abordagem permite a redução de custos, amplia a confiabilidade e funcionalidade do sistema, e agiliza o processo de desenvolvimento do software para atender requisi...

Este artigo discute a importância da avaliação de qualidade em ecossistemas de software, em especial no domínio educacional. São apresentados alguns indicadores de saúde de ecossistemas, utilizando como foco o BROAD-ECOS, um Ecossistema de eLearning baseado em serviços educacionais, reuso e compartilhamento de recursos em um contexto interorganizac...