Ranilson Paiva

Ontology Driven Software Engineering: A Review of Challenges and Opportunities

Ontologies are formal representations of knowledge about a given domain. Based on them, it is possible to create more expressive knowledge bases that can be shared, extended and reused in different scenarios. In software engineering, ontologies can contribute in many different ways to improve the models, methods, techniques and processes of software development. Nevertheless, the use and benefits of ontologies and Semantic Web technologies in Software Engineering is spread across several articles and books available in the literature. In this context, this paper aims at compiling and presenting the research findings and potential benefits when applying ontologies to address three major challenges in software engineering: (1) difficulty in communicating and sharing information; (2) effective management of software development phases; and (3) development techniques and environments to support the production of semantic software through an interdisciplinary approach. We believe that the review of the literature and discussions presented in this work can contribute to disseminate best practices of using ontologies in software development as well as to give directions about this field of research, its challenges and opportunities.

Uma Ferramenta para Recomendação Pedagógica Baseada em Mineração de Dados Educacionais

Este artigo apresenta um modelo para aplicacao de tecnicas de mineracao em dados coletados a partir de avaliacoes da aprendizagem. A partir da proposta, torna-se possivel identificar quais conteudos e em que niveis cognitivos eles foram assimilados pelos aprendizes, permitindo, assim, que estrategicas pedagogicas sejam adequadamente planejadas para grupos de estudantes que apresentem as dificuldades identificadas. Para validar o estudo, sao apresentados tambem os resultados do experimento realizado numa disciplina de Programacao do curso de Licenciatura em Computacao da Universidade de Pernambuco.Os Anais dos Workshops do II Congresso Brasileiro de Informatica na Educacao (CBIE 2013)xa0incluem: VI Workshop sobre Avaliacao e Acompanhamento da Aprendizagem em Ambientes Virtuais (WAvalia13) III Workshop sobre Formacao eExperiencias Educacionais no Programa Um Computador por Aluno (WUCA13) V Workshop Brasileiro de WebSemântica e Educacao (WSWED13) Workshop de Realidade Virtual e Aumentada aplicada a Educacao (WAVE) Concurso de Teses, Dissertacoes e Trabalhos de Conclusao de Curso 2013 (CTD-IE) Painel dos Grupos de Pesquisa em Informatica na Educacao 2013 (PGPIE) Mostra de Praticas de Informatica na Educacao 2013 (MPIE)

Evaluating the Impact of Mars and Venus Effect on the Use of an Adaptive Learning Technology for Portuguese and Mathematics

Some recent studies discussed the pros and cons of gender difference in the use of intelligent educational technologies. According to these studies, there is a difference in behavior, attitude, learning and emotion. However, most of the studies were conducted for Mathematics and in a well developed ecological setting. In this work, we investigated the Mars and Venus Effect, by measuring together different variables, such as learning performance (in Portuguese and Mathematics), age, location area, and learning technology. The study was a random pre/posttest control group experimental design, on which 191 students from public schools in Brazil participated. The experimental group used an adaptive learning technology (called MeuTutor) for nine months, while the control group did not use any educational technology during the study. The most relevant results are: i) the use of the adaptive learning technology improves students performance in Mathematics and Portuguese for both male and female students, ii) the improvement of male students performance is more significant, against female students, iii) when we focus on technology, male students had better performance in mathematics, but no significant difference in Portuguese.

Authoring Tools for Designing Intelligent Tutoring Systems: a Systematic Review of the Literature

Authoring tools have been broadly used to design Intelligent Tutoring Systems (ITS). However, ITS community still lacks a current understanding of how authoring tools are used by non-programmer authors to design ITS. Hence, the objective of this work is to review how authoring tools have been supporting ITS design for non-programmer authors. In order to meet our goal, we conduct a Systematic Literature Review (SLR) to identify the primary studies on the use of ITS authoring tools, following a pre-defined review protocol. Among the 4622 papers retrieved from seven digital libraries published from 2009 to June 2016, 33 papers are finally included after applying our exclusion and inclusion criteria. We then identify the main ITS components authored, the ITS types designed, the features used to facilitate the authoring process, the technologies used to develop authoring tools and the time at which authoring occurs. We also look for evidence of the benefits of ITS authoring tools. In summary, the main findings of this work are: (1) there is empirical evidence of the benefits (i.e., mainly in terms of effectiveness, efficiency, quality of authored artifacts, and usability) of using ITS authoring tools for non-programmer authors, specially to aid authoring of learning content and to support authoring of model-tracing/cognitive and example-tracing tutors; 2) domain and pedagogical models have been much more targeted by authoring tools; (3) several ITS types have been authored, with an emphasis on model-tracing/cognitive and example-tracing tutors; (4) besides providing features for authoring all four ITS components, current authoring tools are also presenting general features (e.g., view learners’ statistics and reuse tutor design) to create broader authoring tools; (5) a great diversity of technologies, which include AI techniques, software solutions and distributed technologies, are used to develop ITS authoring tools; and (6) authoring tools have been mainly targeting ITS design before students’ instruction, but works are also addressing authoring during and/or post-instruction relying both on human and artificial intelligence. We conclude this work by showing several promising research opportunities that are quite important and interesting but underexplored in current research and practice.

Visualizing Learning Analytics and Educational Data Mining Outputs

The increase in supply and demand of on-line courses evidences a new educational paradigm mediated by information and communication technologies. However, an issue in this new paradigm is the high number of students who drop out (85% on average). Some of them blame the lack of instructor support. This support needs the analysis of students’ data to guide teachers’ decision-making. Learning Analytics (LA), Educational Data Mining (EDM) and Data Visualization (DataViz) are some tools for this analysis, but teachers do not receive appropriate technological support to use them. So, we used DataViz to help teachers understand the output from the application of LA and EDM algorithms on the students’ data. We evaluated if instructors understood the information in the visualizations, and asked their opinion about the visualizations’ (1) utility; (2) ease of use; (3) attitude towards use; (4) intention to use; (5) aesthetics; (6) the color scheme used; and (7) the vocabulary used. The results indicate that instructors understood the information in the visualizations and the majority of them had favorable opinions, but we noticed the vocabulary used needs improvement.

Amplifying Teachers Intelligence in the Design of Gamified Intelligent Tutoring Systems

Researchers are increasingly interested in using gamification along with Intelligent Tutoring Systems (ITS) to motivate action, promote learning, facilitate problem-solving, and to drive desired learning behaviors. In fact, although the desire of teachers to be active users of gamified ITS, these systems are not personalized according to teachers’ preferences. Several research problems might arise when trying to empower teachers in the design of gamified ITS, for instance, the high complexity and variability of features to manage, the need to consider theories and design practices, and the need of providing simple and usable solutions for them. In this work, we propose a gamified ITS authoring tool that supports authoring (fully or partially) of the domain, gamification and pedagogical models of gamified ITS by teachers. We investigate how different versions of the tool are perceived by users assuming the role of teachers. Our results indicate a positive attitude towards the use of the authoring tool, in which participants agreed that they are easy to use, usable, simple, aesthetically appealing, have a well-perceived system support and high credibility.

Usability Perspective of an Authoring Solution to Assist Pedagogical Decision-Making

There is a quest to provide education from anywhere, at any time and for anyone, using digital information and communication technologies, but there is no equivalent increase in support for the instructors responsible for maintaining such courses, evidenced by the large number of dropouts and failures. We propose an authoring solution to guide pedagogical decision-making in on-line learning environments to help instructors (1) to discover pedagogical situations occurring in their courses; (2) understand these situation; (3) make decisions to address them; (4) monitor and evaluate the impact from decisions made. However, instructors do not master these abilities, nor is it practical/appropriate to ask them to do so. We developed a proof-of-concept version of an authoring solution, named T-Partner, that guides instructors through these 4 steps. We conducted an experiment to evaluate whether it is perceived as useful and easy to use. The results show that its usefulness and ease of use were positively perceived by the instructors.

Helping MOOC Teachers Do Their Job

There is a quest to provide education from anywhere, at any time and for anyone, using digital information and communication technologies. However, there is no equivalent increase in support for the instructors responsible for maintaining such courses, which is evidenced by the large number of dropouts and failures in such courses, to which learners justify as a lack of support from instructors. Instructors, however, complaint about the huge effort to manage such courses. In order to provide this support, instructors would have to: (1) to discover situations of pedagogical interest occurring in their courses; (2) understand these situations; (3) make decisions to address them; (4) monitor and evaluate the impact of the decision made. However, instructors do not master these abilities, nor is it practical or appropriate to ask them to do so. We propose a process, and an authoring solution that implements it, to guide pedagogical decision-making in online learning environments. Our proposal is based on decision-making informed by educational data and data visualization, with the assistance of an authoring system to promote cooperation between artificial intelligence and human intelligence. We conducted experiments, using a MOOC named MeuTutor-ENEM, to evaluate the process and the authoring solution, and the results indicate that the process helped instructors make better pedagogical decisions, and the authoring solution was positively perceived by the instructors.