Este volume descreve o trabalho multi e interdisciplinar de pesquisa realizado na área de Inteligência Artificial aplicada à Educação, tendo como objetivo principal à proposta de uma metodologia de trabalho suportada por um ambiente na Web como recurso de apoio à aprendizagem almejada pela subárea de Programação Computacional, nos cursos de graduação em Informática. O trabalho investigativo e experimental foi desenvolvido com base na teoria proposta por Ausubel e o ambiente desenvolvido possui arquitetura baseada nos Sistemas Tutores Inteligentes, onde se buscou criar um Assistente Virtual de Ensino Inteligente, cujo comportamento é modelado a partir de um conjunto de regras oriundas da Lógica Fuzzy. Esta base de regras busca estabelecer uma nova forma de análise e assistência no acompanhamento da evolução de aprendizagem do aluno, tendo por base os pressupostos da teoria ausubeliana. A organização dos conteúdos na base de domínio utiliza uma estrutura organizada na forma de Mapas Conceituais, os quais possuem relação com as funções de pertinência associadas aos objetivos destes conteúdos. O trabalho experimental foi realizado na universidade onde o autor trabalha como docente, permitindo que fossem realizadas as análises e entrevistas de forma facilitada. O protótipo, criado para validar alguns aspectos da tese, obteve sucesso e constatou um aproveitamento médio melhor na aprendizagem em Programação Computacional. / This volume describe the multi and interdisciplinary work of made research in the Artificial Intelligence area applied to Education, with the main objective to the purpose of one methodology of work that has the support by Web environment as a way of support for the expected learning by the Computational Programming sub area in the graduation courses of Informatics. The investigative and experimental work was developed based in the theory proposed by Ausubel and the developed environment has the architecture based in the Intelligent Tutoring Systems, looking for a creation of one Intelligent Teaching Assistant, which the behavior is model from the rule group with origin in Fuzzy Logic. This base of rules search to establish one new form of analysis and assistance to go along with evolution of student knowledge, basing in the presuppositions of Subsumption Theory. The organization of contents in the base of dominion use one organized structure in Conceptual Maps form, that have the relation with functions of associated relevant to the objectives of these contents. The experimental work was realized in university where the author works as a teacher, giving the permission to realize the analysis and interviews in the easy way. The prototype, created for some aspect validation of the thesis it was obtained success and it was consisted a medium development better than the learning in the Computacional Programming.

In the classroom, teachers make use of different combinations of social planes (e.g., individual, collaborative) to support learning. However, little is known about the complementary strengths of individual and collaborative learning or how to combine them so that they are more effective than either social plane alone. One roadblock to this investigation is an ability to orchestrate, or manage, more complex, but theoretically effective, combinations of collaborative and individual learning in the classroom. Prior research has created orchestration tools that support the planning and real-time management of classroom activities, which reduces the cognitive load and time needed for instructors to support the activity, allowing for more complex activities to become more manageable. Current orchestration tools do not, however, support a wide range of combinations of collaborative and individual learning activities in a flexible manner. To fully investigate the combinations of collaborative and individual learning, orchestration tools need to be developed that can support the researcher in a way that can be integrated into the classroom by accounting for teachers’ values. My thesis work addresses two related goals. First, my work addresses the questions: Do collaborative and individual learning have complementary strengths and is a combination of the two social planes better than either alone? In my work, I developed an intelligent tutoring system (ITS) to support collaborative and individual learning. Through three studies, using this ITS, with over 500 4th and 5th grade students, I demonstrate that a collaborative ITS can be used to effectively support learning with elementary school students and that a combination of collaborative and individual learning is more effective than either alone. However, my studies did not find any support for complementary strengths and many other combinations of social planes are left to investigate. Additionally, during my experiments, I encountered challenges in orchestration that, along with the need to research more complex combinations of collaborative and individual learning, informed the next steps of my research. The second question my thesis work addresses is: How does an orchestration tool that supports researchers in exploring this space need to be designed to align with teachers’ values for easy integration in the classroom? Specifically, I aimed to support fluid transitions between social planes where students do not all have to be working in sync, which is not currently supported in existing orchestration tools. To support the orchestration tool design, I present a framework that structures the space that a researcher can explore when combining individual and collaborative learning. The framework can act as the set of requirements to be met in the orchestration tool from the point of the researcher as well as a lens to analyze and design combined social plane activities. As a first step towards supporting fluid transitions as laid out in the framework, I present a set of statistical models that extend domain-level individual modeling into the space of collaborative environments. Finally, I developed an orchestration prototype built around my framework that can be used as a research tool to further explore combined collaborative and individual spaces. To develop the tool to be successful within the classroom, I worked with teachers through a co-design process and validation of the prototype to incorporate their values into the tool. Taken together, my dissertation has six primary contributions. My dissertation contributes to the learning sciences through advancing our knowledge of (1) the strengths of collaborative and individual learning, although I did not find any complementary strengths, and (2) if a combination is better than either alone, which I did find support for. It contributes to educational technology through (3) the design of an effective ITS that supports collaborative and individual learning for fractions and educational data mining through (4) the advancement of models that can more accurately predict individual learning within a collaborative setting than the existing individual models. Finally, it contributes to computer supported collaborative learning and human-computer interaction through (5) a framework, which provides a lens for designing and analyzing combined collaborative and individual learning spaces, and (6) an orchestration prototype that supports fluid transitions between social planes in a way that can be a useful to both researchers and teachers in the classroom.

As part of an effort to develop an intelligent tutoring system, a set of knowledge representation frameworks was proposed to represent expert domain knowledge. A general representation of time points and temporal relations was developed to facilitate temporal concept deductions as well as facilitating explanation capabilities vital in an intelligent advisor system. Conventional representations of time use a single-referenced timeline and assigns a single unique value to the time of occurrence of an event. They fail to capture the notion of events, such as changes in signal states in microcomputer systems, which do not occur at precise points in time, but rather over a range of time with some probability distribution. Time is, fundamentally, a relative quantity. In conventional representations, this relative relation is implicitly defined with a fixed reference, "time-zero", on the timeline. This definition is insufficient if an explanation of the temporal relations is to be constructed. The proposed representation of time solves these two problems by representing a time point as a time-range and making the reference point explicit. An architecture of the system was also proposed to provide a means of integrating various modules as the system evolves, as well as a modular development approach. A production rule EXPERT based on the rule framework used in the Graphic Interactive LISP tutor (GIL) [44, 45], an intelligent tutor for LISP programming, was implemented to demonstrate the inference process using this time point representation. The EXPERT is goal-driven and is intended to be an integral part of a complete intelligent tutoring system. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

This master thesis is focused on tutoring systems and their practical usage in education. In the theoretical part of this work is introducted architecture of this systems together with characteristics of types and examples. Next there is a description of systems in programming courses. Based on this knowledge application for teaching Python through feedback to student codes is proposed. Implementation and presentation of tests results, gained in interaction with real users, are introduced in the practical part of the work.

Educators in the United States (U.S.) are increasingly turning to intelligent tutoring systems (ITS) to provide differentiated math instruction to high school students. However, many struggling high school learners do not perform well on these platforms, which reinforces the need for more awareness about effective supports that influence the achievement of learners in these milieus. The purpose of this study was to determine what factors of the Assessment and Learning in Knowledge Spaces (ALEKS), an ITS, are predictive of struggling learners' performance in a blended-learning Algebra 1 course at an inner city technical high school located in the northeastern U.S. The theoretical framework consisted of knowledge base theory, the zone of proximal development, and cognitive learning theory. Three variables (student retention, engagement time, and the ratio of topics mastered to topics practiced) were used to predict the degree of association on the criterion variable (mathematics competencies), as measured by final course progress grades in algebra, and the Preliminary Scholastic Assessment Test (PSATm) math scores. A correlational predictive design was applied to assess the data of a purposive sample of 265 struggling students at the study site; multiple regression analysis was also used to investigate the predictability of these variables. Findings suggest that engagement time and the ratio of mastered to practiced topics were significant predictors of final course progress grades. Nevertheless, these factors were not significant contributors in predicting PSATm score. Retention was identified as the only statistically significant predictor of PSATm score. The results offer educators with additional insights that can facilitate improvements in mathematical content knowledge and promote higher graduation rates for struggling learners in high school mathematics.

Computer-based instructors, just like their human counterparts, should monitor the emotional and cognitive states of their students in order to adapt instructional technique. Doing so requires a model of student state to be available at run time, but this has historically been difficult. Because people are different, generalized models have not been able to be validated. As a person’s cognitive and affective state vary over time of day and seasonally, individualized models have had differing difficulties. The simultaneous creation and execution of an individualized model, in real time, represents the last option for modeling such cognitive and affective states. This dissertation presents and evaluates four differing techniques for the creation of cognitive and affective models that are created on-line and in real time for each individual user as alternatives to generalized models. Each of these techniques involves making predictions and modifications to the model in real time, addressing the real time datastream problems of infinite length, detection of new concepts, and responding to how concepts change over time. Additionally, with the knowledge that a user is physically present, this work investigates the contribution that the occasional direct user query can add to the overall quality of such models. The research described in this dissertation finds that the creation of a reasonable quality affective model is possible with an infinitesimal amount of time and without “ground truth” knowledge of the user, which is shown across three different emotional states. Creation of a cognitive model in the same fashion, however, was not possible via direct AI modeling, even with all of the “ground truth” information available, which is shown across four different cognitive states.

Emotional intelligence has a prominent role in education, health care, and day to day interaction. With the increasing use of computer technology, computers are interacting with more and more individuals. This interaction provides an opportunity to increase knowledge about human emotion for human consumption, well-being, and improved computer adaptation. This thesis explores the efficacy of using up to four different sensors in three domains for computational affect detection. We first consider computer-based education, where a collection of four sensors is used to detect student emotions relevant to learning, such as frustration, confidence, excitement and interest while students use a computer geometry tutor. The best classier of each emotion in terms of accuracy ranges from 78% to 87.5%. We then use voice data collected in a clinical setting to differentiate both gender and culture of the speaker. We produce classifiers with accuracies between 84% and 94% for gender, and between 58% and 70% for American vs. Asian culture, and we find that classifiers for distinguishing between four cultures do not perform better than chance. Finally, we use video and audio in a health care education scenario to detect students' emotions during a clinical simulation evaluation. The video data provides classifiers with accuracies between 63% and 88% for the emotions of confident, anxious, frustrated, excited, and interested. We find the audio data to be too complex to single out the voice source of the student by automatic means. In total, this work is a step forward in the automatic computational detection of affect in realistic settings.

This dissertation presents a novel effort to develop ITS technologies that adapt by observing student behavior. In particular, we define an evolving expert knowledge base (EEKB) that structures a domain's information as a set of nodes and the relationships that exist between those nodes. The structure of this model is not the particularly novel aspect of this work, but rather the model's evolving behavior. Past efforts have shown that this model, once created, is useful for providing students with expert feedback as they work within our ITS called Rashi. We present an algorithm that observes groups of students as they work within Rashi, and collects student contributions to form an accurate domain level EEKB. We then present experimentation that simulates more than 15,000 data points of real student interaction and analyzes the quality of the EEKB models that are produced. We discover that EEKB models can be constructed accurately, and with significant efficiency compared to human constructed models of the same form. We are able to make this judgment by comparing our automatically constructed models with similar models that were hand crafted by a small team of domain experts. We also explore several tertiary effects. We focus on the impact that gaming and game mechanics have on various aspects of this model acquisition process. We discuss explicit game mechanics that were implemented in the source ITS from which our data was collected. Students who are given our system with game mechanics contribute higher amounts of data, while also performing higher quality work. Additionally, we define a novel type of game called a knowledge-refinement game (KRG), which motivates subject matter experts (SMEs) to contribute to an already constructed EEKB, but for the purpose of refining the model in areas in which confidence is low. Experimental work with the KRG provides strong evidence that: 1) the quality of the original EEKB was indeed strong, as validated by KRG players, and 2) both the quality and breadth of knowledge within the EEKB are increased when players use the KRG.

No description available.

No description available.