Search

O presente trabalho explora a hipótese de predição da nota ENEM em ciências humanas a partir de dados pedagógicos oriundos de notas de avaliações escolares de estudantes de ensino médio de um colégio particular em São Paulo. A partir da análise, foi possível a predição da nota ENEM de ciências humanas no decurso do 3º ano do ensino médio com uma correlação (r de Pearson) de 60,2% e RMSE de 39,7 pontos na escala ENEM. O modelo apontou, ainda, conteúdos relevantes fortemente correlacionados com o desempenho ENEM já desde o 1º ano do ensino médio.

Protocol for an umbrella review of systematic reviews at CHI.

Gamification is frequently employed in learning environments to enhance learner interactions and engagement. However, most games use pre-scripted dialogues and interactions with players, which limit their immersion and cognition. Our aim is to develop a semantic matching tool that enables users to introduce open text answers which are automatically associated with the most similar pre-scripted answer. A structured scenario written in Dutch was developed by experts for this communication experiment as a sequence of possible interactions within the environment. Semantic similarity scores computed with the SpaCy library were combined with string kernels, WordNet-based distances, and used as features in a neural network. Our experiments show that string kernels are the most predictive feature for determining the most probable pre-scripted answer, whereas neural networks obtain similar performance by combining multiple semantic similarity measures.

Gamification has become a significant direction in designing technologies, services, products, organizational structures, and any human activities towards being more game-like and consequently being more engaging and motivating. Albeit its success, research indicates that personal differences exist with regards to susceptibility to gamification at large as well as to different types of gamification designs. As a response, models and measurement instruments of user types when it comes to gamification have been developed. One of the most discussed related instruments is the Hexad user types scale. However, there has been paucity of research related to the validity and reliability of the Hexad instrument in general but also of its different formulations and language versions. To face this gap, our study focused on analyzing the psychometric properties of the Hexad scale in Brazilian Portuguese by conducting two confirmatory factor analyses and two multi-group confirmatory factor analyses. The survey was answered by 421 Brazilian respondents (52% self-reported women, 47% self-reported men, 0.5% preferred not to provide their gender, and 0.5% checked the option “other”), from the five Brazilian regions (23 different states and the Federal District), and aged between 10 and 60 years old. Findings support the structural validity of the scale as an oblique model and indicate opportunities for small improvements. Further research, both at academy and practice, may use this study as the source of measurement of user types related to gamification (in Brazilian Portuguese), as well as, as a theoretical and practical source for further studies discussing personalized gamification.

In recent years, studies in different areas have used gamification to improve users' flow experience. However, due to the high variety of the conducted studies and the lack of secondary studies (e.g., systematic literature reviews) in this field, it is difficult to get the state-of-the-art of this research domain. To address this problem, we conducted a systematic literature review to identify i) which gamification design methods have been used in the studies about gamification and Flow Theory, ii) which gamification elements have been used in these studies, iii) which methods have been used to evaluate the users' flow experience in gamified settings, and iv) how gamification affects users' flow experience. The main results show that there is growing interest to this field, as the number of publications is increasing. The most significant interest is in the area of gamification in education. However, there is no unanimity regarding the preferred method of the study or the effects of gamification on users' experience. Our results highlight the importance of conducting new experimental studies investigating how gamification affects the users' flow experience in different gamified settings, applications and domains., 5th International GamiFIN Conference 2021 (GamiFIN 2021), April 7-10, 2021, Finland

Hypothesis testing is a challenging topic for many students in introductory university statistics courses. In this paper we explore how automated feedback in an Intelligent Tutoring System can foster students’ ability to carry out hypothesis tests. Students in an experimental group (N = 163) received elaborate feedback on the structure of the hypothesis testing procedure, while students in a control group (N = 151) only received verification feedback. Immediate feedback effects were measured by comparing numbers of attempted tasks, complete solutions, and errors between the groups, while transfer of feedback effects was measured by student performance on follow-up tasks. Results show that students receiving elaborate feedback solved more tasks and made fewer errors than students receiving only verification feedback, which suggests that students benefited from the elaborate feedback.

This paper presents a model that characterizes textual discourse contents of online groups and provides a visualization of the level of collaboration within groups. This approach is envisioned to provide an insight into a real-time intervention to scaffold collaboration within online learning groups.

This paper presents a systematic literature review (SLR) that investigates group formation, as a first step towards automated group formation for collaborative learning. Out of 105 papers selected for review, after using specific selection and a quality assessment method, a final list of 21 relevant studies was selected for analysis. The review revealed the current state of the art in group formation.

Semantic Web-based educational systems (SWBES) are Web-based educational platforms designed to solve several problems faced by users, such as difficulties related to searching, sharing and reuse of educational resources. Ensuring the quality of these systems requires knowledge about technologies in different knowledge' areas. So far, there is no model for evaluating SWBES and, so, we have developed an approach to quality assessment that considers its multidisciplinary. This study aimed to present the approach and its evaluation, through case studies. The results showed that it is adequate, mainly for integrating the main quality criteria in a single instrument. Os sistemas educacionais baseados em Web Semântica (SWBES) são plataformas desenvolvidas para resolver diversos problemas enfrentados pelos usuários, relacionados à busca, compartilhamento e reuso de recursos educacionais. Garantir a qualidade desses sistemas exige conhecimento sobre tecnologias em diferentes áreas do conhecimento. Não existe, até o momento, um modelo para avaliar SWBES e, por isso, foi desenvolvida uma abordagem para avaliação de qualidade que considera sua multidisciplinaridade. Este trabalho objetiva apresentar a abordagem e sua avaliação, por meio de estudos de caso. Os resultados mostraram que é adequada, principalmente por integrar os principais critérios de qualidade num único instrumento

This paper presents a systematic literature review (SLR) that investigates group formation, as a first step towards automated group formation for collaborative learning. Out of 105 papers selected for review, after using specific selection and a quality assessment method, a final list of 21 relevant studies was selected for analysis. The review revealed the current state of the art in group formation.

One of the challenges approached by the community of emergency situation assessment and management is to determine a process of informational analysis to assist operators in developing Situational Awareness (SAW). Due to the complexity in data and uncertainty in its quality, besides the dynamicity in monitored environments, operators are susceptible to errors in their SAW, decreasing the chance of an assertive decision-making. In this context, correctly representing information about the situation, while they are gathered and processed, will contribute to better orient operators and systems regarding the ongoing situation. To this end, the goal of this paper is to contribute to the production of enhanced inputs in the situation assessment of forest fires for the DFWithoutFire project. More specifically, this paper presents the development of an ontology that aggregates information on data quality, promoting an improved representation of data about fires. A study case of a forest fire emergency response is showed to demonstrate the applicability of the ontology with the quality management. Results present a semantic representation model that is capable of receiving instances extracted from human intelligence data that originated from crowdsourcing and evaluated quantitatively on aspects of data quality. Para a comunidade de avaliação e gerenciamento de situações de emergências, determinar um processo de análise informacional para o desenvolvimento da Consciência da Situação (SAW) é um desafio, devido à limitada qualidade e complexidade dos dados, além da dinamicidade de ambientes reais monitorados. Operadores de sistemas de avaliação de situações de emergência, expostos a dados de qualidade incerta, estão suscetíveis a erros de SAW, diminuindo suas chances de uma tomada de decisão assertiva. Neste contexto, representar corretamente informações sobre tais situações, à medida que são coletadas e processadas, vai contribuir para melhor orientar humanos e sistemas sobre o que de fato acontece num ambiente de interesse. O presente trabalho visa contribuir com o problema de produção de melhores insumos na avaliação de situações de incêndios florestais, no âmbito do projeto DF100Fogo, apresentando o desenvolvimento de uma ontologia que agrega informações sobre a qualidade dos dados, promovendo ao operador de sistemas de emergência, uma melhor representação de dados sobre os incêndios. Um estudo de caso envolvendo um atendimento a uma situação de incêndio florestal será mostrado para demonstrar a aplicabilidade da ontologia junto à gestão da qualidade. Resultados apresentam um modelo de representação semântica, capaz de receber instâncias extraídas de dados de inteligência humana, com origem em sensoriamento participativo, e avaliadas quantitativamente sob aspectos de qualidade da informação.

This article presents the results of an experiment in which we investigated how prior algebra knowledge and personality can influence the permanence time from the confusion state to frustration/boredom state in a computer learning environment. Our experimental results indicate that people with a neurotic personality and a low level of algebra knowledge can deal with confusion for less time and can easily feel frustrated/bored when there is no intervention. Our analysis also suggest that people with an extroversion personality and a low level of algebra knowledge are able to control confusion for longer, leading to later interventions. These findings support that it is possible to detect emotions in a less invasive way and without the need of physiological sensors or complex algorithms. Furthermore, obtained median times can be incorporated into computational regulation models (e.g. adaptive interfaces) to regulate students' emotion during the teaching-learning process., 13 pages, 1 figure

Modeling an ontology is a hard and time-consuming task. Although methodologies are useful for ontologists to create good ontologies, they do not help with the task of evaluating the quality of the ontology to be reused. For these reasons, it is imperative to evaluate the quality of the ontology after constructing it or before reusing it. Few studies usually present only a set of criteria and questions, but no guidelines to evaluate the ontology. The effort to evaluate an ontology is very high as there is a huge dependence on the evaluator's expertise to understand the criteria and questions in depth. Moreover, the evaluation is still very subjective. This study presents a novel methodology for ontology evaluation, taking into account three fundamental principles: i) it is based on the Goal, Question, Metric approach for empirical evaluation; ii) the goals of the methodologies are based on the roles of knowledge representations combined with specific evaluation criteria; iii) each ontology is evaluated according to the type of ontology. The methodology was empirically evaluated using different ontologists and ontologies of the same domain. The main contributions of this study are: i) defining a step-by-step approach to evaluate the quality of an ontology; ii) proposing an evaluation based on the roles of knowledge representations; iii) the explicit difference of the evaluation according to the type of the ontology iii) a questionnaire to evaluate the ontologies; iv) a statistical model that automatically calculates the quality of the ontologies.

This paper presents a model that characterizes textual discourse contents of online groups and provides a visualization of the level of collaboration within groups. This approach is envisioned to provide an insight into a real-time intervention to scaffold collaboration within online learning groups.

Aprendizagem colaborativa é um paradigma que pressupõe que alunos trabalhem em grupos, compartilhando conhecimento e ajudando uns aos outros na resolução de dúvidas e problemas que são comuns no processo de ensino e aprendizagem. Porém, a tarefa de formação e acompanhamento dos grupos não é trivial, visto que existem diversas variáveis que não só influenciam na composição, mas também no comportamento dos membros de cada grupo. Visando interações positivas que tornem o aprendizado mais efetivo e duradouro para os alunos, este artigo tem como objetivo investigar os aspectos culturais na formação de grupos de aprendizagem.

Neste trabalho discute-se o papel de destaque que a Geometria Interativa (GI) tem adquirido no contexto do ensino de Geometria assistida por computador, enfatizando alguns dos benefícios da GI para professores e alunos. De um lado, auxilia o professor em sua tarefa de criar material didático mais interativo e desenvolver atividades que estimulam a curiosidade. De outro lado, proporciona ao aluno um ambiente no qual a postura participativa e a busca por desafios promovem a troca de experiências e a maturidade para compreender o conteúdo geométrico. Neste contexto, serão apresentados resultados de experiências didáticas realizadas em cursos de licenciatura em matemática e de extensão universitária para professores, utilizando um software de GI chamado iGeom. Além disso, introduz-se como soluções geométricas podem ser didaticamente apresentadas como algoritmos e como é possível implementar algoritmos geométricos com laços repetitivos de modo automático no iGeom facilitando a abordagem de conceitos matemáticos como progressões geométricas, somatórios, convergência, entre outros. This work discusses the key role played by the Interactive Geometry Software (IGS) in the process of teaching and learning geometry with computational support. We present the important benefits of IGS for teachers and students. On the one hand it helps the teacher in his task of creating more interactive teaching materials and develop activities that stimulate curiosity. On the other hand it provides students with an environment in which the active behavior and the pursuit of challenges promote the acquisition of experiences and the maturity that will lead them to understand the geometrical content. In this context, we present results of didactic activities using a IGS, referred to as iGeom, in undergraduate courses for pre-service math teachers. We also discuss how geometric constructions can be seem as algorithms and how it is possible to implement automatic recursive algorithms on iGeom facilitating the introduction of mathematical concepts such as geometric progressions, series, convergence, among others.

Erroneous examples are an instructional technique that hold promise to help children learn. In the study reported in this paper, sixth and seventh grade math students were presented with erroneous examples of decimal problems and were asked to explain and correct those examples. The problems were presented as interactive exercises on the Internet, with feedback provided on correctness of the student explanations and corrections. A second (control) group of students were given problems to solve, also with feedback on correctness. With over 100 students per condition, an erroneous example effect was found: students who worked with the interactive erroneous examples did significantly better than the problem solving students on a delayed posttest. While this finding is highly encouraging, our ultimate research question is this: how can erroneous examples be adaptively presented to students, targeted at their most deeply held misconceptions, to best leverage their effectiveness? This paper discusses how the results of the present study will lead us to an adaptive version of the erroneous examples material.21st Century Learning for 21st Century Skills 21st Century Learning for 21st Century Skills LookInsideShareShare this content on Facebook Share this content on Twitter Share this content on LinkedInOther actions Export citations About this Book

We present a novel method for analysing speaker alignment in second language conversational practice dialogue. In particular, we represent utterances as Dialogue Acts, and use Epistemic Network Analysis to analyse their usage patterns. We hypothesise convergence between speakers will be visible at this level, and influenced by learner ability and tutor strategy. We find as student ability increases, the distribution of student and tutor Dialogue Acts is both initially closer, and converges more over the course of the dialogue. We also find that the type of Dialogue Act use changes both with ability and throughout an interaction. Our results contribute a novel method for the automatic analysis of both learner ability and tutor strategy, which can inform both the development of personalised automatic tutoring tools, and formative assessment and feedback in an educational setting.

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. In this sense, the objective of this work is to develop and validate a method for predicting student dropout using data from the first two weeks of study, to allow for early intervention. Instead of the classical questionnaire-based method, we opted for a non-subjective, data-driven approach. However, such approaches are known to suffer from a potential overload of factors, which may not all be relevant to the prediction task. As a result, we reached a very promising 80% of accuracy, and performed explicit extraction of the main factors leading to student dropout.

© Springer Nature Switzerland AG 2019. Reflective writing is widely acknowledged to be one of the most effective learning activities for promoting students’ self-reflection and critical thinking. However, manually assessing and giving feedback on reflective writing is time consuming, and known to be challenging for educators. There is little work investigating the potential of automated analysis of reflective writing, and even less on machine learning approaches which offer potential advantages over rule-based approaches. This study reports progress in developing a machine learning approach for the binary classification of pharmacy students’ reflective statements about their work placements. Four common statistical classifiers were trained on a corpus of 301 statements, using emotional, cognitive and linguistic features from the Linguistic Inquiry and Word Count (LIWC) analysis, in combination with affective and rhetorical features from the Academic Writing Analytics (AWA) platform. The results showed that the Random-forest algorithm performed well (F-score = 0.799) and that AWA features, such as emotional and reflective rhetorical moves, improved performance.

Submitted by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-06-04T13:02:42Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Filipe Dwan.pdf: 3617202 bytes, checksum: 21261ba9c1db7a40af29004bd0bb6f52 (MD5) Approved for entry into archive by Divis??o de Documenta????o/BC Biblioteca Central (ddbc@ufam.edu.br) on 2018-06-04T13:02:58Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Filipe Dwan.pdf: 3617202 bytes, checksum: 21261ba9c1db7a40af29004bd0bb6f52 (MD5) Made available in DSpace on 2018-06-04T13:02:58Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Filipe Dwan.pdf: 3617202 bytes, checksum: 21261ba9c1db7a40af29004bd0bb6f52 (MD5) Previous issue date: 2018-03-29 CS1 (first year programming) classes are known to have a high dropout and non-pass rate. Thus, there have been many studies attempting to predict and alleviate CS1 student performance. Knowing about student performance in advance can be useful for many reasons. For example, teachers can apply specific actions to help learners who are struggling, as well as provide more challenging activities to high-achievers. Initial studies used static factors, such as: high school grades, age, gender. However, student behavior is dynamic and, as such, a data-driven approach has been gaining more attention, since many universities are using web-based environments to support CS1 classes. Thereby, many researchers have started extracting student behavior by cleaning data collected from these environments and using them as features in machine learning (ML) models. Recently, the research community has proposed many predictive methods available, even though many of these studies would need to be replicated, to check if they are context-sensitive. Thus, we have collected a set of successful features correlated with the student grade used in related studies, compiling the best ML attributes, as well as adding new features, and applying them on a database representing 486 CS1 students. The set of features was used in ML pipelines which were optimized with two approaches: hyperparameter-tuning with random search and genetic programming. As a result, we achieved an accuracy of 74.44%, using data from the first two weeks to predict student final grade, which outperforms a state-of-the-art research applied to the same dataset. It is also worth noting that from the eighth week of class, the method achieved accuracy between 85% and 90.62%. Em m??dia, um ter??o dos alunos no mundo reprova em disciplinas de introdu????o ?? programa????o de computadores (IPC). Assim, muitos estudos v??m sendo conduzidos a fim de inferir o desempenho de estudantes de turmas de IPC. Inicialmente, pesquisadores investigavam a rela????o das notas dos alunos com fatores est??ticos como: notas no ensino m??dio, g??nero, idade e outros. Entretanto, o comportamento dos estudantes ?? din??mico e, dessa forma, abordagens orientadas aos dados v??m ganhando aten????o, uma vez que muitas universidades utilizam ambientes web para turmas de programa????o como ju??zes online. Com efeito, muitos pesquisadores v??m extraindo e tratando os dados dos estudantes a partir desses ambientes e usando-os como atributos de algoritmos de aprendizagem de m??quina para a constru????o de modelos preditivos. No entanto, a comunidade cient??fica sugere que tais estudos sejam reproduzidos a fim de investigar se eles s??o generaliz??veis a outras bases de dados educacionais. Neste sentido, neste trabalho apresentou-se um m??todo que emprega um conjunto de atributos correlacionados com as notas dos estudantes, sendo alguns baseados em trabalhos relacionados e outros propostos nesta pesquisa, a fim de realizar a predi????o do desempenho dos alunos nas avalia????es intermedi??rias e nas m??dias finais. Tal m??todo foi aplicado a uma base de dados com 486 alunos de IPC. O conjunto de atributos chamado de perfil de programa????o foi empregado em algoritmos de aprendizagem de m??quina e otimizado utilizando duas abordagens: a) ajuste de hiperpar??metros com random search e b) constru????o do pipeline de aprendizagem de m??quina utilizando algoritmos evolutivos. Como resultado, atingiu-se 74,44% de acur??cia na tarefa de identificar se os alunos iriam ser reprovados ou aprovados usando os dados das duas semanas de aula em uma base de dados balanceada. Esse resultado foi estatisticamente superior ao baseline. Destaca-se ainda que a partir da oitava semana de aula, o m??todo atingiu acur??cias entre 85% e 90,62%.

Submitted by Maria Medeiros (maria.dilva1@ufcg.edu.br) on 2018-06-04T13:17:59Z No. of bitstreams: 1 DIEGO DERMEVAL MEDEIROS DA CUNHA MATOS - TESE (PPGCC) 2017.pdf: 5848671 bytes, checksum: b890812e50eefda440fc048fd77b0f93 (MD5) Made available in DSpace on 2018-06-04T13:17:59Z (GMT). No. of bitstreams: 1 DIEGO DERMEVAL MEDEIROS DA CUNHA MATOS - TESE (PPGCC) 2017.pdf: 5848671 bytes, checksum: b890812e50eefda440fc048fd77b0f93 (MD5) Previous issue date: 2017-03-17 Sistemas Tutores Inteligentes (STIs) têm recibo a atenção de acadêmicos e profissionais desde da década de 70. Tem havido um grande número de estudos recentes em apoio da efetividade de STIs. Entretanto, é muito comum que estudantes fiquem desengajados ou entediados durante o processo de aprendizagem usando STIs. Para considerar explicitamente os aspectos motivacionais de estudantes, pesquisadores estão cada vez mais interessados em usar gamificação em conjunto com STIs. Contudo, apesar de prover tutoria individualizada para estudantes e algum tipo de suporte para professores, estes usuários não têm recebido alta prioridade no desenvolvimento destes tipos de sistemas. De forma a contribuir para o uso ativo e personalizado de STIs gamificados por professores, três problemas técnicos devem ser considerados. Primeiro, projetar STI é muito complexo (deve-se considerar diferentes teorias, componentes e partes interessadas) e incluir gamificação pode aumentar significativamente tal complexidade e variabilidade. Segundo, as funcionalidades de STIs gamificados podem ser usadas de acordo com vários elementos (ex.: nível educacional, domínio de conhecimento, teorias de gamificaçãoe STI, etc). Desta forma, é imprescindível tirar proveito das teorias e práticas de ambos os tópicos para reduzir o espaço de design destes sistemas. Terceiro, para efetivamente auxiliar professores a usarem ativamente estes sistemas, faz-se necessário prover uma solução simples e usável para eles. Para lidar com estes problemas, o principal objetivo desta tese é projetar uma solução computacional de autoria para fornecer aos professores uma forma de personalizar as funcionalidades de STIs gamificados gerenciando a alta variabilidade destes sistemas e considerando as teorias/práticas de gamificação e STI. Visando alcançar este objetivo, nós identificamos o espaço de variabilidade e o representamos por meio do uso de uma abordagem de modelagem de features baseada em ontologias (OntoSPL). Desenvolvemos um modelo ontológico integrado (Ontologia de tutoria gamificada ou Gamified tutoring ontology) que conecta elementos de design de jogos apoiados por evidências no domínio de e-learning, além de teorias e frameworks de gamificação aos conceitos de STI. Finalmente, desenvolvemos uma solução de autoria (chamada AGITS) que leva em consideração tais ontologias para auxiliar professores na personalização de funcionalidades de STIs gamificados. As contribuições deste trabalho são avaliadas por meio da condução de quatro estudos empíricos: (1) conduzimos um experimento controlado para comparar a OntoSPL com uma abordagem de modelagem de features bem conhecida na literatura. Os resultados sugerem que esta abordagem é mais flexível e requer menos tempo para mudar; (2) avaliamos o modelo ontológico integrado usando um método de avaliação de ontologias (FOCA) com especialistas tanto de contexto acadêmico quanto industrial. Os resultados sugerem que as ontologias estão atendendo adequadamente os papeis de representação do conhecimento; (3) avaliamos versões não-interativas da solução de autoria desenvolvida com 59 participantes. Os resultados indicam uma atitude favorável ao uso da solução de autoria projetada,nos quais os participantes concordaram que a solução é fácil de usar, usável, simples, esteticamente atraente,tem um suporte bem percebido e alta credibilidade; e (4) avaliamos, por fim,versões interativas (do zero e usando um modelo) da solução de autoria com 41 professores. Os resultados sugerem que professores podem usar e reusar, com um alto nível de aceitação, uma solução de autoria que inclui toda a complexidade de projetar STI gamificado. Intelligent Tutoring Systems (ITSs) have been drawing the attention of academics and practitioners since early 70’s. There have been a number of recent studies in support of the effectiveness of ITSs. However, it is very common that students become disengaged or bored during the learning process by using ITSs. To explicitly consider students’ motivational aspects, researchers are increasingly interested in using gamification along with ITS.However, despite providing individualized tutoring to students and some kind of support for teachers, teachers have been not considered as first-class citizens in the development of these kinds of systems. In order to contribute to the active and customized use of gamified ITS by teachers, three technical problems should be considered. First, designing ITS is very complex (i.e., take into account different theories, components, and stahekolders) and including gamification may significantly increase such complexity and variability. Second, gamified ITS features can be used depending on several elements (e.g., educational level, knowledge domain, gamification and ITS theories, etc). Thus, it is imperative to take advantage of theories and practices from both topics to reduce the design space of these systems. Third, in order to effectively aid teachers to actively use such systems, it is needed to provide a simple and usable solution for them. To deal with these problems, the main objective of this thesis is to design an authoring computational solution to provide for teachers a way to customize gamified ITS features managing the high variability of these systems and considering gamification and ITS theories/practices. To achieve this objective, we identify the variability space and represent it using an ontology-based feature modeling approach (OntoSPL). We develop an integrated ontological model (Gamified tutoring ontology) that connects evidence-supported game design elements in the e-learning domain as well as gamification theories and frameworks to existing ITS concepts. Finally, we develop an authoring solution (named AGITS) that takes into account these ontologies to aid teachers in the customization of gamified ITS features. We evaluate our contributions by conducting four empirical studies: (1) we perform a controlled experiment to compare OntoSPL against a well-known ontology-based feature modeling approach. The results suggest that our approach is more flexible and requires less time to change; (2) we evaluate the ontological integrated model by using an ontology evaluation method (FOCA) with experts from academic and industrial settings. The results suggest that our ontologies are properly targeting the knowledge representation roles; (3) we evaluate non-interactive versions of the designed authoring solution with 59 participants. The results indicate a positive attitude towards the use of the designed authoring solutions, in which participants agreed that they are ease to use, usable, simple, aesthetically appealing, have a well-perceived system support and high credibility; and (4) we also evaluate interactive versions (scratch and template) of our authoring solution with 41 teachers. The results suggest that teachers can use and reuse, with a high acceptance level, an authoring solution that includes all the complexity to design gamified ITS.

The new Information and Communication Technologies (ICT) are making the relationship between people more dynamic, establishing new ways of sharing Information and Knowledge. These new relationships allow us to build Social Networks with purposes of information sharing, experiences and multimedia resources, such as Facebook, Twitter, WhatsApp, LinkedIn, Instagram, Researchgate, Mendeley,and so on, specific for services offering such as transportation (Uber, Cabify, EasyGo), accommodation (Airbnb, HouseTrip), personal assistants (Google Now), among other types of applications. For this sharing process to be efficiently performed, those resources must be sought, found and integrated based on the meaning they store, taking into account the particularities of user-defined meanings. This knowledge must be processed and represented in a way that allows the integration in a uniform, automatic and safe way, with meanings being negotiated among users. This Thesis presents a model of Information and Knowledge Sharing and Knowledge between peers through a point-to-point negotiation using Ontological Alignment established by means of an inter-language, created based on the WKI method. This method is integrated into the WProfile collaborative platform, enabling environment users to manage the knowledge of their local multimedia repository. An ontological social network is established from the interaction between the environment users , in which social bonds are created from the semantic interlanguage between the local ontologies, aligning the common meanings between peers. As novas Tecnologias de Informação e Comunicação (TIC) estão tornando o relacionamento entre as pessoas mais dinâmico, estabelecendo novas formas de compartilhamento de Informação e Conhecimento. Estes novos relacionamentos permitem a construção de diferentes tipos de Redes Sociais com a finalidade de compartilhamento de informações, experiências e recursos multimídia como, por exemplo: Facebook, Twitter, Whatsapp, LinkedIn, Instagram, Researchgate, Mendeley, etc., específicas para ofertas de serviços como Carona (Uber, Cabify, EasyGo); Moradia (Airbnb, HouseTrip), Assistentes pessoais (Google Now), entre outros tipos de aplicativos. Para que este processo de compartilhamento possa ser efetuado de forma eficiente, as tarefas de busca, localização e integração devem ser realizadas com base no significado do conteúdo que armazenam, levando-se em consideração a particularidade do significado estabelecido pelos usuários. Este conhecimento deve ser processado e representado de forma a permitir a integração de maneira uniforme e automática, segura e com o significado negociado entre os usuários. Esta Tese apresenta um modelo de Compartilhamento de Informações e Conhecimento entre pares, através de uma negociação ponto a ponto, utilizando Alinhamento de Ontologias estabelecido através de uma interlíngua, criada a partir do método WKI. Este método é integrado à plataforma colaborativa WProfile viabilizando aos usuários do ambiente a gestão do conhecimento de seu repositório de recursos multimídia. A partir da interação entre os usuários do ambiente é estabelecida uma rede social ontológica, em que os laços sociais são criados a partir do laço das interlínguas semânticas entre as ontologias locais, alinhando os significados comuns entre os pares.

The Semantic Web (WS) is be coming an important research topic in Computer Science. One of reasons is the possibility of representing information in semantic way using ontologies, assisting in the building of applications which are able to use data, be coming more scalable and intelligent. As a result, many new applications have been developed using the Semantic Web technologies such as RDF, SPARQL and ontologies themselves. Although software development using these technologies is complicated and costly, the community of WS has been producing tools and APIs (application programming interface) to support programmers in the development of semantic applications. Among the most important APIs developed by the community are those that provide mechanisms for handling ontologies. Currently, there are two main approaches used by manipulation APIs: i) RDF triples and objet-oriented programming (OOP). On the one hand, using the RDF triples, the developers have to manipulate the ontologies using only triples, making the development process more complicated. On the other hand, the OOP APIs promote ontologies manipulation using object, which facilitates the development. Although several APIs are been developed in order to manipulate ontologies at object level, most of them are not being evaluated, especially when related to the quality of attributes, such as performance and scalability. Moreover, the high quantity and variability of APIs require a more generic approach in order to deal with these issues, be cause building an evaluation system for each API is a costly task and does not allow the reuse of the solution, neither of its modules. Therefore, this work presents an architecture-entered framework, named JOINT-Evaluator (JOINT-E), where the developers will be able to evaluate the APIs based on a set of pre-defined performance and scalability metrics. It is important to note that the framework also enables the analysis and comparison of the data with statistical support, in creasing the credibility and reliability of the results. To validate the work three scenarios were created on experiment. The main APIs (Alibaba and Jastor) used by developers were tested and evaluated. Furthermore, a qualitative analysis is presented, showing the statistical results and highlighting the advantages and disadvantages of each API. The results have showed that Jastor surpass Alibaba in many issues. Finally, a survey was applied to developers in order to validate the framework. This suvery have presented that this work attend a developers demand. Coordenação de Aperfeiçoamento de Pessoal de Ní­vel Superior A Web Semântica (WS) vem se tornando um importante tópico de pesquisa na Ciência da Computação. Uma das razões é a possibilidade de representar a informação de maneira semântica por meio de ontologias. Como consequência, inúmeras aplicações têm sido desenvolvidas utilizando as tecnologias da Web semântica, tais como, RDF, SPARQL e as próprias ontologias. Embora o desenvolvimento de software utilizando estas tecnologias seja complicado e custoso, a comunidade da WS vem produzindo ferramentas e APIs (application programming interface) para apoiar programadores no desenvolvimento de aplicações semânticas. Nesse cenário, existem atualmente duas principais abordagens utilizadas por essas APIs para manipulação de ontologias: triplas RDF e Programação Orientada a Objetos (POO). Por um lado, o uso de APIs para manipular triplas RDF permite que o desenvolvedor crie aplicações mapeando as propriedades das classes presentes nas triplas RDF em código utilizando uma linguagem de programação (e.g. Java). Por outro lado, existem as APIs para manipular ontologias utilizando o paradigma de orientação a objetivo. Isso permite que desenvolvedores continuem utilizando um paradigma já conhecido e largamente utilizado. Embora várias APIs tenham sido desenvolvidas para manipular ontologias no ní­vel de objeto, a maioria não foi adequadamente avaliada, principalmente no que se refere aos atributos de qualidade de desempenho e escalabilidade. Além disso, a alta quantidade e a variabilidade das APIs faz com que seja necessário construir uma abordagem genérica que lide com essas questões, uma vez que construir um sistema de avaliação para cada API isoladamente é inviável. Dessa forma, este trabalho apresenta um framework centrado na arquitetura, chamado JOINT-E (Java Ontology Integration Toolkit-Evaluator), que permite a desenvolvedores avaliar as APIs para manipulação de ontologias. Para realizar esta avaliação foi objetivo deste trabalho definir um conjunto de métricas de desempenho e escalabilidade. Frisa-se que o framework e as métricas definidas possibilitam a análise e comparação das APIs com apoio estatí­stico, aumentando a credibilidade e confiabilidade dos resultados. Para validar os resultados obtidos foi proposto um experimento com três cenários usando as principais APIs (Alibaba e Jastor) utilizadas pela comunidade de desenvolvimento de aplicativos semântico. De acordo com este experimento a Jastor apresentou melhor performance em relação ao Alibaba levando em consideração as métricas propostas. Por fim, realizou-se também uma pesquisa de opinião com desenvolvedores para verificar se o framework JOINT-E oferece informações importantes para tomada de decisão referente a escolha de uma API. Os resultados desta pesquisa constaram que o framework oferece meios mais precisos para avaliação das APIs e atende a demanda dos desenvolvedores.

In the last few years, it is increasing the development and use of ontologies in creating more intelligent and effective applications that aim to solve problems commonly found on the Web. This popularity is due to the fact that ontologies attempt to provide semantics to the data consumed by machines, so that they can reason about these data. However, the large adoption of the Semantic Web can be further accelerated by providing sophisticated tools that lower the barrier to the development of applications based on RDF and OWL. Developers of applications with relational databases are already familiar with tools like Hibernate, which provide an object-relational mapping and the management of the objects states. Actually, the main object state that Hibernate provides is the detached. Nevertheless, the great majority of the object-ontology mapping systems (OOMS) only provide persistent objects. The big difference between these two types of objects is that the former one has its life cycle independent of the underlying triple store connection, but the latter one is bounded to the connection. In this context, this paper proposes the creation of an object-ontology mapping systems that supports detached objects, called Joint-DE. With this system, developers of ontology-based applications can: i) use the objects coming from the triple store as objects of the business model; ii) use such objects as data transfer objects ( DTOs) between subsystems and; iii) develop small transactions with detached objects that represent a long transaction unit for the application user. To illustrate the benets of the proposed system, a case study of a real application is presented, outlining the architectural limitations of the application using an existing OOMS in the literature, as well as showing positive results to the use of JOINT-DE. Finally, an experiment was planned and executed aiming to compare the JOINT-DE with another OOMS widely used by the community: Alibaba. The statistical analyzes performed in this experiment showed satisfactory results with regard to JOINT-DE. Coordenação de Aperfeiçoamento de Pessoal de Nível Superior Nos últimos anos, é crescente o desenvolvimento e o uso de ontologias na criação de aplicações mais inteligentes e eficazes que têm como objetivo solucionar problemas encontrados comumente na Web. Toda essa popularidade se deve ao fato de que ontologias tentam oferecer semântica aos dados consumidos pelas máquinas de forma que ela possa raciocinar sobre estes dados. Todavia, a larga adoção da Web Semântica pode ser ainda acelerada ao prover ferramentas sofisticadas que diminuam a barreira de desenvolvimento de aplicações baseadas em RDF e OWL. Desenvolvedores de aplicações com bancos de dados relacionais já estão acostumados com ferramentas como o Hibernate, que oferecem um mapeamento objeto-relacional e o gerenciamento de estados dos objetos. Na verdade, o principal estado de objeto que o Hibernate disponibiliza é o desconectado. Entretanto, a grande maioria dos sistemas de mapeamento objeto-ontologia (OOMS) apenas disponibiliza objetos persistentes. A grande diferença entre os dois tipos de objetos é que o primeiro tem seu ciclo de vida independente da conexão com o banco de dados RDF, já o último é limitado à conexão. Neste contexto, este trabalho propõe a criação de um sistema de mapeamento objeto-ontologia que suporta objetos desconectados, chamado JOINT-DE. Com este sistema, desenvolvedores de aplicações baseados em ontologias podem: i) utilizar os objetos oriundos do banco de dados RDF como objetos do modelo de negócio, transitando nas diversas camadas da aplicação; ii) utilizar esses objetos como objetos de transferência de dados (DTOs) entre subsistemas e iii) desenvolver pequenas transações com objetos desconectados que representam uma unidade longa de transação para o usuário da aplicação. Para exemplificar os benefí­cios do sistema proposto, um estudo de caso de uma aplicação real é apresentado, expondo as limitações arquiteturais dessa aplicação ao utilizar um OOMS existente na literatura, além de mostrar resultados favoráveis à implantação do JOINT-DE. Por fim, um experimento foi planejado e executado com o objetivo de comparar o JOINT-DE com outro OOMS bastante utilizado pela comunidade: Alibaba. As análises estatí­sticas realizadas nesse experimento apontaram resultados satisfatórios com relação ao JOINT-DE.

This paper presents a framework for educational data mining based on semantic web services as a solution to the challenges found in this area such as data and methods standardization, educational environments integration and easier to use mining tools for both educators and non-specialist users. The solution also includes a wizard, which aims to facilitate the extension and instantiation of the proposed framework in di erent products. In order to validate the proposed solution, a case study was also performed using data from a real e-learning environment used by students from distance mode courses. Fundação de Amparo a Pesquisa do Estado de Alagoas Este trabalho apresenta um framework para mineração de dados educacionais baseado em serviços web semânticos como uma solução para os desa os encontrados na área, como: padronização de métodos e dados, integração entre ambientes educacionais e ferramentas de mineração e ferramentas mais intuitivas para o uso de educadores e não especialistas. A solução proposta também inclui um wizard, que auxilia na extensão e instanciação do framework proposto em diferentes produtos. Para validar a solução proposta, foi realizado um estudo de caso utilizando dados de um ambiente e-Learning real utilizado por estudantes de um curso da modalidade a distância.