As one of the central problems in the area of Intelligent Tutoring Systems (ITSs), student modelling has been widely used to assist in systems’ decision making and students’ learning. On the one hand, by reasoning about students’ knowledge in the instructional domain, a system is able to adapt its pedagogical actions in order to provide a customized learning environment. These actions may include individualized problem-selection, tailored instructions and feedback, as well as updating the presentation of student models. On the other hand, students can reflect on their own learning progress by viewing individual Open Student Models (OSMs) and enhance their meta-cognitive skills by learning from the system’s estimation of their knowledge levels. It is believed that making the information in the student model available to students can raise students’ awareness of their strengths and weaknesses in the corresponding domain and hence allow them to develop a more effective and efficient way of learning. An OSM has been developed in EER-Tutor. EER-Tutor is a web-enhanced ITS that supports university students in learning conceptual database modelling. Students design Enhanced Entity-Relationship (EER) diagrams and receive different level of feedback in a problem-solving environment. The pedagogical decisions on feedback generation and problem selection are made according to student models. Previously, student models in EER-Tutor are presented to students on request as skill meters. Skill meters have been proved useful in helping students to improve their meta-cognitive skills. However, as the simplest presentation of a student model, skill meters contain very limited information. Some studies show that an OSM with multiple views is more effective since it supports individual preferences and different educational purposes. The focus of our work is to develop a variety of presentations for the OSM in EER-Tutor. For this purposes, we have modified the system to include not only skill meters but also other presentation styles. An evaluation study has been performed after the development. Both subjective and objective results have been collected. This thesis presents the extended EER-Tutor, followed by the analysis of the evaluation study.

Predicting student performance is an important part of the student modeling task in Intelligent Tutoring System (ITS). The state-of-art model for predicting student performance - Bayesian Knowledge Tracing (KT) has many critical limitations. One specific limitation is that KT has no underlying mechanism for memory decay represented in the model, which means that no forgetting is happening in the learning process. In addition we notice that numerous modification to the KT model have been proposed and evaluated, however many of these are often based on a combination of intuition and experience in the domain, leading to models without performance improvement. Moreover, KT is computationally expensive, model fitting procedures can take hours or days to run on large datasets. The goal of this research work is to improve the accuracy of student performance prediction by incorporating the memory decay factor which the standard Bayesian Knowledge Tracing had ignored. We also propose a completely data driven and inexpensive approach to model improvement. This alternative allows for researchers to evaluate which aspects of a model are most likely to result in model performance improvements based purely on the dataset features that are computed from ITS system logs.

A utilização da Web com objetivos educacionais e de treinamento, vem se caracterizando como uma das grandes áreas de pesquisa e aplicação da informática no dia-a-dia das pessoas e empresas. A tecnologia de workflow poderá contribuir decisivamente para a qualidade dos cursos na Web, permitindo que a informação seja apresentada de maneira interativa conduzindo o aprendiz a uma atitude dinâmica, transformando-o num elemento ativo que manipula os recursos na seqüência e velocidade desejados, o que contribui para um aprendizado mais eficiente. A utilização de workflow associada a tecnologia de Agentes fornece o potencial de uma navegação não-linear, onde o usuário dispõe de flexibilidade para determinar o fluxo de apresentação das informações, não vinculado a uma cadeia seqüencial de conteúdos que foram hierarquicamente construídos. Neste contexto, o presente trabalho, apresenta um modelo de aluno especificado através de um modelo de Workflow. Este modelo foi alcançado por meio da análise das interações de uma amostra de alunos em um curso na Web, observando a Teoria Cognitiva dos Estilos de Aprendizagem e a ordem de execução das atividades do curso pelos alunos. A finalidade desta modelagem por workflow tem como objetivo contribuir nas atividades de execução, coordenação, monitoramento e adaptação em cursos na Internet. / The use of the Web with educational and training objectives may be identified as one of the great research and application areas of computer science today. The workflow technology will be able to contribute decisively for the quality of the Web courses, allowing the information to be presented in interactive way leading the apprentice to a dynamic attitude, transforming the content management into an active element that manipulates the resources in the desired sequence and speed, contributing for a more efficient learning. The use of dynamic workflows associated the agent technology supplies the potential of a nonlinear navigation, where the user takes profit of system flexibility to determine the flow of presentation of the information, not tied with a sequential chain of contents or a hierarchical structure as they have being constructed. In this context, the present work, develop a student model specified through a workflow model. This model was reached by the analysis of the interactions of a sample of students in a Web course. The Cognitive Theory of the Styles of Learning and the order of execution of the activities of the course for the students have being considered in the model development. The purpose of this workflow modelling was to contribute in the development of a comprehensive model of activities execution, coordination, monitoring and adaptation in courses in the Internet.

A utilização da Web com objetivos educacionais e de treinamento, vem se caracterizando como uma das grandes áreas de pesquisa e aplicação da informática no dia-a-dia das pessoas e empresas. A tecnologia de workflow poderá contribuir decisivamente para a qualidade dos cursos na Web, permitindo que a informação seja apresentada de maneira interativa conduzindo o aprendiz a uma atitude dinâmica, transformando-o num elemento ativo que manipula os recursos na seqüência e velocidade desejados, o que contribui para um aprendizado mais eficiente. A utilização de workflow associada a tecnologia de Agentes fornece o potencial de uma navegação não-linear, onde o usuário dispõe de flexibilidade para determinar o fluxo de apresentação das informações, não vinculado a uma cadeia seqüencial de conteúdos que foram hierarquicamente construídos. Neste contexto, o presente trabalho, apresenta um modelo de aluno especificado através de um modelo de Workflow. Este modelo foi alcançado por meio da análise das interações de uma amostra de alunos em um curso na Web, observando a Teoria Cognitiva dos Estilos de Aprendizagem e a ordem de execução das atividades do curso pelos alunos. A finalidade desta modelagem por workflow tem como objetivo contribuir nas atividades de execução, coordenação, monitoramento e adaptação em cursos na Internet. / The use of the Web with educational and training objectives may be identified as one of the great research and application areas of computer science today. The workflow technology will be able to contribute decisively for the quality of the Web courses, allowing the information to be presented in interactive way leading the apprentice to a dynamic attitude, transforming the content management into an active element that manipulates the resources in the desired sequence and speed, contributing for a more efficient learning. The use of dynamic workflows associated the agent technology supplies the potential of a nonlinear navigation, where the user takes profit of system flexibility to determine the flow of presentation of the information, not tied with a sequential chain of contents or a hierarchical structure as they have being constructed. In this context, the present work, develop a student model specified through a workflow model. This model was reached by the analysis of the interactions of a sample of students in a Web course. The Cognitive Theory of the Styles of Learning and the order of execution of the activities of the course for the students have being considered in the model development. The purpose of this workflow modelling was to contribute in the development of a comprehensive model of activities execution, coordination, monitoring and adaptation in courses in the Internet.

A utilização da Web com objetivos educacionais e de treinamento, vem se caracterizando como uma das grandes áreas de pesquisa e aplicação da informática no dia-a-dia das pessoas e empresas. A tecnologia de workflow poderá contribuir decisivamente para a qualidade dos cursos na Web, permitindo que a informação seja apresentada de maneira interativa conduzindo o aprendiz a uma atitude dinâmica, transformando-o num elemento ativo que manipula os recursos na seqüência e velocidade desejados, o que contribui para um aprendizado mais eficiente. A utilização de workflow associada a tecnologia de Agentes fornece o potencial de uma navegação não-linear, onde o usuário dispõe de flexibilidade para determinar o fluxo de apresentação das informações, não vinculado a uma cadeia seqüencial de conteúdos que foram hierarquicamente construídos. Neste contexto, o presente trabalho, apresenta um modelo de aluno especificado através de um modelo de Workflow. Este modelo foi alcançado por meio da análise das interações de uma amostra de alunos em um curso na Web, observando a Teoria Cognitiva dos Estilos de Aprendizagem e a ordem de execução das atividades do curso pelos alunos. A finalidade desta modelagem por workflow tem como objetivo contribuir nas atividades de execução, coordenação, monitoramento e adaptação em cursos na Internet. / The use of the Web with educational and training objectives may be identified as one of the great research and application areas of computer science today. The workflow technology will be able to contribute decisively for the quality of the Web courses, allowing the information to be presented in interactive way leading the apprentice to a dynamic attitude, transforming the content management into an active element that manipulates the resources in the desired sequence and speed, contributing for a more efficient learning. The use of dynamic workflows associated the agent technology supplies the potential of a nonlinear navigation, where the user takes profit of system flexibility to determine the flow of presentation of the information, not tied with a sequential chain of contents or a hierarchical structure as they have being constructed. In this context, the present work, develop a student model specified through a workflow model. This model was reached by the analysis of the interactions of a sample of students in a Web course. The Cognitive Theory of the Styles of Learning and the order of execution of the activities of the course for the students have being considered in the model development. The purpose of this workflow modelling was to contribute in the development of a comprehensive model of activities execution, coordination, monitoring and adaptation in courses in the Internet.

Adaptive learning is a crucial part in intelligent tutoring systems. It provides students with appropriate tutoring interventions, based on students’ characteristics, status, and other related features, in order to optimize their learning outcomes. It is required to determine students’ knowledge level or learning progress, based on which it then uses proper techniques to choose the optimal interventions. In this dissertation work, I focus on these aspects related to the process in adaptive learning: student modeling, k-armed bandits, and contextual bandits. Student modeling. The main objective of student modeling is to develop cognitive models of students, including modeling content skills and knowledge about learning. In this work, we investigate the effect of prerequisite skill in predicting students’ knowledge in post skills, and we make use of the prerequisite performance in different student models. As a result, this makes them superior to traditional models. K-armed bandits. We apply k-armed bandit algorithms to personalize interventions for students, to optimize their learning outcomes. Due to the lack of diverse interventions and small difference of intervention effectiveness in educational experiments, we also propose a simple selection strategy, and compare it with several k-armed bandit algorithms. Contextual bandits. In contextual bandit problem, additional side information, also called context, can be used to determine which action to select. First, we construct a feature evaluation mechanism, which determines which feature to be combined with bandits. Second, we propose a new decision tree algorithm, which is capable of detecting aptitude treatment effect for students. Third, with combined bandits with the decision tree, we apply the contextual bandits to make personalization in two different types of data, simulated data and real experimental data.

Esta dissertação de mestrado está inserida no trabalho desenvolvido pelo grupo de pesquisa GIA/UFRGS e situa-se na área de Inteligência Artificial aplicada à Educação à Distância apresentando uma arquitetura distribuída no desenvolvimento de Ambientes de Ensino Inteligentes. A Web facilita aos alunos encontrarem informações relevantes ao estudo que estão fazendo. Outra vantagem do ensino na Web é o indivíduo ser sabedor da existência da informação e de onde ela se localiza para que no momento adequado a acesse. Porém, o progresso que se poderá ter na área de informática aplicada à educação dependerá da adequação e qualidade do software educacional a ser utilizado. Por isso, temos que ter software de ensino inteligentes, que possam trazer esta qualidade e adequação conforme o aluno que está tentando adquirir um certo conhecimento. O objetivo principal do presente trabalho se propõe a estudar as diferentes técnicas e mecanismos de se construir um modelo do aluno adaptativo na Web, aplicáveis em um cenário de educação à distância, a partir de um ambiente distribuído de ensino-aprendizagem inteligente baseado em uma arquitetura multiagentes que contempla o paradigma de ensino cooperativo (uma sociedade de agentes humanos e artificiais, que cooperam para alcançar um objetivo comum). Além disso, o trabalho propõe o uso de estratégias de ensino segundo regras estipuladas pelo especialista. O agente responsável por este controle observa as modificações do comportamento do aprendiz durante a sua interação no ambiente, e seleciona uma estratégia de acordo com o desempenho do aprendiz. / This master’s degree dissertation was developed within the research group GIA/UFRGS, and is located in the field of Artificial Intelligence applied to distance learning, presenting a distributed architecture to develop intelligent teaching environments. The Web make easier for students to find important information for the study hey are performing. Another advantage of learning on the Web is that one knows the information exist and where they are located in order to access it at the right moment. However, the advances in the area of learning applied computing will depend of the adaptation and quality of the educational software used. Thus, we need intelligent teaching software, which can bring us this quality and adaptation according to the student that is trying to acquire some knowledge. The main goal of this work is to propose to study the different techniques and mechanisms for building an adaptive student model on the Web, that are applicable in a distance learning scenario, from an intelligent teaching-learning distributed environment based in a multi-agent architecture that contemplate the cooperative teaching paradigm (a society of human and artificial agent, which cooperate to reach a common goal). In addition, this work proposes the use of teaching strategies according to rules given by the specialist. The agent responsible for this control observes the apprentice behavioral changes during his interaction with the environment and selects a strategy according to the apprentice performance.

Esta dissertação de mestrado está inserida no trabalho desenvolvido pelo grupo de pesquisa GIA/UFRGS e situa-se na área de Inteligência Artificial aplicada à Educação à Distância apresentando uma arquitetura distribuída no desenvolvimento de Ambientes de Ensino Inteligentes. A Web facilita aos alunos encontrarem informações relevantes ao estudo que estão fazendo. Outra vantagem do ensino na Web é o indivíduo ser sabedor da existência da informação e de onde ela se localiza para que no momento adequado a acesse. Porém, o progresso que se poderá ter na área de informática aplicada à educação dependerá da adequação e qualidade do software educacional a ser utilizado. Por isso, temos que ter software de ensino inteligentes, que possam trazer esta qualidade e adequação conforme o aluno que está tentando adquirir um certo conhecimento. O objetivo principal do presente trabalho se propõe a estudar as diferentes técnicas e mecanismos de se construir um modelo do aluno adaptativo na Web, aplicáveis em um cenário de educação à distância, a partir de um ambiente distribuído de ensino-aprendizagem inteligente baseado em uma arquitetura multiagentes que contempla o paradigma de ensino cooperativo (uma sociedade de agentes humanos e artificiais, que cooperam para alcançar um objetivo comum). Além disso, o trabalho propõe o uso de estratégias de ensino segundo regras estipuladas pelo especialista. O agente responsável por este controle observa as modificações do comportamento do aprendiz durante a sua interação no ambiente, e seleciona uma estratégia de acordo com o desempenho do aprendiz. / This master’s degree dissertation was developed within the research group GIA/UFRGS, and is located in the field of Artificial Intelligence applied to distance learning, presenting a distributed architecture to develop intelligent teaching environments. The Web make easier for students to find important information for the study hey are performing. Another advantage of learning on the Web is that one knows the information exist and where they are located in order to access it at the right moment. However, the advances in the area of learning applied computing will depend of the adaptation and quality of the educational software used. Thus, we need intelligent teaching software, which can bring us this quality and adaptation according to the student that is trying to acquire some knowledge. The main goal of this work is to propose to study the different techniques and mechanisms for building an adaptive student model on the Web, that are applicable in a distance learning scenario, from an intelligent teaching-learning distributed environment based in a multi-agent architecture that contemplate the cooperative teaching paradigm (a society of human and artificial agent, which cooperate to reach a common goal). In addition, this work proposes the use of teaching strategies according to rules given by the specialist. The agent responsible for this control observes the apprentice behavioral changes during his interaction with the environment and selects a strategy according to the apprentice performance.

Esta dissertação de mestrado está inserida no trabalho desenvolvido pelo grupo de pesquisa GIA/UFRGS e situa-se na área de Inteligência Artificial aplicada à Educação à Distância apresentando uma arquitetura distribuída no desenvolvimento de Ambientes de Ensino Inteligentes. A Web facilita aos alunos encontrarem informações relevantes ao estudo que estão fazendo. Outra vantagem do ensino na Web é o indivíduo ser sabedor da existência da informação e de onde ela se localiza para que no momento adequado a acesse. Porém, o progresso que se poderá ter na área de informática aplicada à educação dependerá da adequação e qualidade do software educacional a ser utilizado. Por isso, temos que ter software de ensino inteligentes, que possam trazer esta qualidade e adequação conforme o aluno que está tentando adquirir um certo conhecimento. O objetivo principal do presente trabalho se propõe a estudar as diferentes técnicas e mecanismos de se construir um modelo do aluno adaptativo na Web, aplicáveis em um cenário de educação à distância, a partir de um ambiente distribuído de ensino-aprendizagem inteligente baseado em uma arquitetura multiagentes que contempla o paradigma de ensino cooperativo (uma sociedade de agentes humanos e artificiais, que cooperam para alcançar um objetivo comum). Além disso, o trabalho propõe o uso de estratégias de ensino segundo regras estipuladas pelo especialista. O agente responsável por este controle observa as modificações do comportamento do aprendiz durante a sua interação no ambiente, e seleciona uma estratégia de acordo com o desempenho do aprendiz. / This master’s degree dissertation was developed within the research group GIA/UFRGS, and is located in the field of Artificial Intelligence applied to distance learning, presenting a distributed architecture to develop intelligent teaching environments. The Web make easier for students to find important information for the study hey are performing. Another advantage of learning on the Web is that one knows the information exist and where they are located in order to access it at the right moment. However, the advances in the area of learning applied computing will depend of the adaptation and quality of the educational software used. Thus, we need intelligent teaching software, which can bring us this quality and adaptation according to the student that is trying to acquire some knowledge. The main goal of this work is to propose to study the different techniques and mechanisms for building an adaptive student model on the Web, that are applicable in a distance learning scenario, from an intelligent teaching-learning distributed environment based in a multi-agent architecture that contemplate the cooperative teaching paradigm (a society of human and artificial agent, which cooperate to reach a common goal). In addition, this work proposes the use of teaching strategies according to rules given by the specialist. The agent responsible for this control observes the apprentice behavioral changes during his interaction with the environment and selects a strategy according to the apprentice performance.

Adaptyviose sistemose prisitaikymas prie besimokančiojo yra paremtas duomenų apie besimokantįjį rinkimu, analizavimu ir mokymosi aplinkos pritaikymu besimokančiojo poreikiams. Tam būtina parinkti tokius „sekimo“ duomenis, pagal kuriuos būtų galima daryti išvadas sistemos lygmenyje. Šie duomenys turi būti suprantami sistemai, nuolat atnaujinami, lengvai surenkami. Jie gali būti įvairūs, pradedant nuorodų paspaudimo laiku, baigiant akies žvilgsnio nukreipimo vieta. Pagal tai sistema gali transformuoti duomenis ir – priklausomai nuo savo paskirties – duoti patarimus ar tam tikromis priemonėmis pavaizduoti naudingą informaciją, tuo pačiu atsižvelgdama į rezultatus. Tačiau daugelis šių sistemų yra tik prototipo stadijoje arba naudojamos nesudėtingiems procesams vykdyti. Mums žinomos adaptyvios sistemos yra skirtos vieno dalyko probleminei sričiai. Šiame darbe tirsime besimokančiojo modelio perteikimo galimybę virtualioje mokymo(si) aplinkoje (VMA), kai besimokantysis dalyvauja viename arba keliuose nuotoliniuose kursuose. / In adaptive systems adaptation to learner is defined by collection of data about learner, collected data analysis and learning environment adaptation to learners needs. Looking forward to this goal it is necessary to select such logging data, which can be used to make conclusions in a system level. Such data should be acceptable to system, interactive and easy to collect. Data used can be various, starting from click time of the link ending with eye look direction angle. Such system can provide data transformations and depending on purpose, give suggestions. Using necessary tools depict useful information, reacting to results. Most of currently build systems are only in prototype stage or are used for unsophisticated process. Most of them are one subject systems. In this work we address a possibility of student model’s depiction in a VLE, when student participate in one or more than one distance course.