Many colleges face a lack of academic and emotional support for their computer science students. Previous research into this problem produced Maria, a virtual teaching assistant (TA). This initial version of Maria was able to answer student questions, provide error explanations, and praise students for effort on programming assignments. This research continues work on the Maria project with three design goals: (1) reducing obstacles to use of Maria, (2) allowing Maria to provide better academic support, and (3) allowing Maria to provide better emotional support (with less focus on this goal). Improvements were made to the initial version of Maria, including increasing the number of questions that Maria could answer, allowing Maria to suggest questions for students to ask, and adding longer back-and-forth dialogs between Maria and students. Following this, Maria was deployed to students for an evaluation. The evaluation revealed that certain features were popular (including the longer dialogs and easier access to error explanation) and that Maria was unable to provide relevant answers to many questions asked by students. Using data from the evaluation, more improvements were made to Maria to address some of her shortcomings and build on her popular features. Answers to more questions were added for questions about testing, general knowledge questions, questions about many other topics. Many of these new answers used the popular back-and-forth dialog feature. Additionally, this research discusses a system that could be used to automate the creation of new answers for Maria or any virtual teaching assistant using crowdsourcing. / Master of Science / Many colleges face a lack of academic and emotional support for their computer science students. Previous research into this problem produced Maria, a virtual teaching assistant (TA). This initial version of Maria was able to answer student questions, provide error explanations, and praise students for effort on programming assignments. This research continues work on the Maria project with three design goals: (1) reducing obstacles to use of Maria, (2) allowing Maria to provide better academic support, and (3) allowing Maria to provide better emotional support (with less focus on this goal). Improvements were made to the initial version of Maria, including increasing the number of questions that Maria could answer, allowing Maria to suggest questions for students to ask, and adding longer back-and-forth dialogs between Maria and students. Following this, Maria was deployed to students for an evaluation. The evaluation revealed that certain features were popular (including the longer dialogs and easier access to error explanation) and that Maria was unable to provide relevant answers to many questions asked by students. Using data from the evaluation, more improvements were made to Maria to address some of her shortcomings and build on her popular features. Answers to more questions were added for questions about testing, general knowledge questions, questions about many other topics. Many of these new answers used the popular back-and-forth dialog feature. Additionally, this research discusses a system that could be used to automate the creation of new answers for Maria or any virtual teaching assistant using crowdsourcing.

Researchers and educators have always strived for creating appropriate instructional tools and resources that help students to acquire knowledge. Animated pedagogical agents (APAs) embedded within multimedia learning settings are one of the emerging technologies that provide a powerful and supportive learning environment. According to previous studies, APAs can effectively promote learning and support social interaction with learners (Johnson & Lester, 2016; Lane, 2016). However, APAs also may cause cognitive load without providing motivational benefits in some cases and distract learners during the learning process. In other words, the results of previous studies on APAs do not provide enough evidence to argue that APA may be able to decrease cognitive load, promote motivational effects, or facilitate meaningful learning. The lack of enough evidence in the research findings seems to be variable depending upon the APA’s features, the learners, and the difficulty of the learning materials (Schroeder & Adesope, 2014). By focusing on these factors, this study provided new considerations related to embedding an APA’s role that facilitates “Word Parts” for adult students who speak English as a Second Language (ESL) with concentrating on their cognition, motivation, and vocabulary acquisition. Presenting two APA’s roles (expert model and peer model) differently influenced ESL learners’ motivation, specifically their satisfaction feelings. In addition, ESL learners’ prior knowledge affected their intrinsic and extraneous cognitive load, motivation, and vocabulary acquisition. The two different APA’s roles and their effects on ESL learners’ perceptions and learning outcomes serve as a media comparison research. Further, examining APA as a model to teach ESL students vocabulary acquisition skills serves a Computer-Assisted Language Learning (CALL) research.

abstract: The purpose of this study was to investigate the effects of static pedagogical agents (included and excluded) and gamification practice (included and excluded) on vocabulary acquisition and perceptions of cognitive load by junior high students who studied Navajo language via computer-based instructional program. A total of 153 students attending a junior high school in the southwestern United States were the participants for this study. Prior to the beginning of the study, students were randomly assigned to one of four treatment groups who used a Navajo language computer-based program that contained a combination of static pedagogical agent (included and excluded) and gamification practice (included and excluded). There were two criterion measures in this study, a vocabulary acquisition posttest and a survey designed both to measure students’ attitudes toward the program and to measure cognitive load. Anecdotal observations of students’ interactions were also examined. Results indicated that there were no significant differences in posttest scores among treatment conditions; students were, however, generally successful in learning the Navajo vocabulary terms. Participants also reported positive attitudes toward the Navajo language content and gamification practice and expressed a desire to see additional content and games during activities of this type. These findings provide evidence of the impact that computer-based training may have in teaching students an indigenous second language. Furthermore, students seem to enjoy this type of language learning program. Many also indicated that, while static agent was not mentioned, gamification practice may enhance students’ attitudes in such instruction and is an area for future research. Language learning programs could include a variety of gamification practice activities to assist student to learn new vocabulary. Further research is needed to study motivation and cognitive load in Navajo language computer-based training. / Dissertation/Thesis / Doctoral Dissertation Educational Technology 2018

This research examined how four different animated pedagogical agent implementations, which focus on perceptual and inquiry arousal conditions of attention as defined in Keller’s ARCS model of motivational design (Keller, 2009), impact English language learners' situational interest, cognitive load, and reading comprehension in online readings tasks. Animated pedagogical agents (APA) are computer characters embodied with speech, gestures, or movement (Sweller, Ayres, & Kalyuga, 2011), which according to cognitive-affective theory of learning with media (CATLM; Moreno, 2005; Moreno & Mayer, 2007), can provide a mechanism for triggering situational interest in reading materials through different arousal conditions. In this study, perceptual arousal and inquiry arousal were implemented in two different levels within four APA conditions: high perceptual arousal and high inquiry arousal condition, high perceptual and low inquiry condition, low perceptual and high inquiry condition, and low perceptual and low inquiry condition. Study outcome variables included situational interest, cognitive load, and reading comprehension. Situational interest is a psychological construct defined as a specific person-to-topic relationship, which is triggered by the instructional environment during the first stage of a 4-phase model of interest development (Hidi & Renninger, 2006; Krapp, 2002). In this study, situational interest was operationally defined as a self-reported degree of attention and an affective reaction to environmental stimuli; situational interest was measured using a 6-item, 5-point Likert-scale instrument adopted from Rotgans and Schmidt’s (2011b) experiment. Cognitive load is defined in cognitive load theory as a mental effort in working memory, part of which may contribute to formation of mental schemas in long-vi term memory structures (Sweller et al., 1998, p. 259). In this study, three types of cognitive load were examined, including extraneous cognitive load, intrinsic cognitive load, and germane cognitive load. The three types of cognitive load were operationally defined as self-reported complexity, clarity and effectiveness of the presentation, and increase in knowledge and understanding of a topic. The three types of cognitive load were measured using a 10-item, 11-point Likert-scale questionnaire, which was validated in prior studies (Leppink et al., 2013). The last outcome variable, reading comprehension, was measured using multiple-choice recall and understanding questions included with each original text passage. This study did not find any evidence of perceptual or inquiry arousal effects on situational interest, however, disordinal interaction between perceptual and inquiry arousal levels on germane cognitive load was found. Also, a main effect of inquiry arousal levels on reading comprehension was discovered.

The goal of this research is to develop Animated Pedagogical Agents (APA) that can convey clearly perceivable emotions through speech, facial expressions and body gestures. In particular, the two studies reported in the thesis investigated the extent to which modifications to the range of movement of 3 beat gestures, e.g., both arms synchronous outward gesture, both arms synchronous forward gesture, and upper body lean, and the agent ‘s gender have significant effects on viewer’s perception of the agent’s emotion in terms of valence and arousal. For each gesture the range of movement was varied at 2 discrete levels. The stimuli of the studies were 8 12-seconds animation clips generated using a fractional factorial design; in each clip an animated agent who speaks and gestures, gives a lecture segment on binomial probability. 4 clips featured a female agent and 4 clips featured a male agent. In the first study, which used a within-subject design and metric conjoint analysis, 120 subjects were asked to watch the 8 stimuli clips and rank them according to perceived valence and arousal (from highest to lowest). In the second study, which used a between-subject design, 300 participants were assigned to two groups of 150 subjects each. One group watched the 4 clips featuring the male agent and one group watched the 4 clips featuring the female agent. Each participant was asked to rate perceived valence and arousal for each clip using a 7-point Likert scale. Results indicated that extending the arms outwards and forwards as well as modifying the agent’s gender from male to female increased perceived valence and arousal, whereas rotating the body backwards increased only perceived valence.

The purpose of this study was to investigate the impact of the mathematics anxiety treatment messages in a computer-based environment on ninth-grade students' mathematics anxiety and mathematics learning. The study also examined whether the impact of the treatment messages would be differentiated by learner's gender and by learner's prior mathematics anxiety levels (High vs. Medium vs. Low). Participants were 161 ninth-grade students, who took a required introductory algebra class in a public high school neighboring Utah State University. The learning environment was integrated with a pedagogical agent (animated human-like character) as a tutor. This study employed a pretest and posttest experimental design. Participants' mathematics anxiety was measured at the beginning and at the end of the intervention; participants' mathematics learning was measured before and after each lesson (four lessons in total). The participants were randomly assigned to work with either an agent presenting mathematics anxiety treatment messages (TR) or an agent without presenting the treatment messages (NoTR). Because of student attrition, only 128 students were included for data analysis. The results suggested that mathematics anxiety treatment messages provided by a pedagogical agent had no impact on student mathematics anxiety and mathematics learning. Second, there were no main or interaction effects of the treatment messages and learners' gender on mathematics anxiety and mathematics learning. Third, there were significant interaction effects between treatment messages and learner's prior mathematics anxiety levels only on current mathematics anxiety (p < .05). High-anxious students in the TR condition decreased their anxiety more than those in the NoTR condition. Medium-anxious students in the TR condition increased their anxiety whereas those in the NoTR condition decreased their anxiety. Low-anxious students in the TR condition did not change their anxiety whereas those in the NoTR condition increased their anxiety.

Esta é uma pesquisa quanti-qualitativa de estudo de caso que parte de princípios da teoria sociocultural aplicada à área de Aquisição de Segunda Língua (SL) e Língua Estrangeira (LE) e estudos de Informática na Educação a fim de investigar os efeitos da mediação de um agente pedagógico (AP) com estratégias de mediação específicas na aprendizagem colaborativa de inglês como LE em um ambiente virtual. A partir do aporte teórico desenvolvido, a metodologia desta pesquisa envolveu não só a elaboração e a aplicação de uma sequência de atividades de uso da tecnologia em tarefas colaborativas, mas, principalmente, no desenvolvimento de uma ferramenta AP integrado a uma ferramenta de mineração textual capaz de fazer intervenções nas discussões de textos em língua inglesa em uma sala de bate-papo. O contexto da pesquisa constituiu-se de uma turma de 25 estudantes de graduação em Letras/Inglês de uma universidade federal da região sul do Brasil. Primeiramente, os alunos responderam a um questionário que visou estabelecer o perfil desses aprendizes quanto ao uso da língua e da tecnologia. A coleta de dados se deu durante 6 encontros no laboratório de informática, em que os aprendizes realizaram em grupos 5 tarefas colaborativas de discussão de textos com a mediação do AP. Após as tarefas, os alunos responderam a questionários que buscaram investigar a sua percepção sobre o uso do AP na realização das tarefas e em sua aprendizagem. As interações, o uso das funções do AP e os dados dos questionários foram analisados em busca de indícios da mediação do AP no processo de aprendizagem. Com esses resultados, buscou-se contribuir na área de Informática na Educação para a pesquisa sobre o impacto de agentes pedagógicos na aprendizagem de línguas estrangeiras, sugerindo soluções para melhorar a educação apoiada por computador. Na área de Aquisição de SL/LE, pretendeu-se, ainda, trazer novos dados sobre estudos de tarefas colaborativas através da investigação da interação com o AP como um novo elemento para a comunicação mediada por computador na aprendizagem de línguas. / This is a quanti-litative case study that parts of theory sociocultural principles applied to Second Language (SL) and Foreign Language (FL) Acquisition and studies in Computers in Education in order to investigate the effects of a pedagogical agent's (PA) mediation with specific mediation strategies in English as a foreign language (EFL) collaborative learning in a virtual environment. From the theoretical framework developed, the methodology of this research involved not only the development and application of a sequence of activities using technology in EFL collaborative tasks, but mainly in the development of a PA integrated into a textual mining tool capable of doing interventions in reading discussions in a chat room. The context of the research consisted of a class of 25 graduate students in English Language and Literature in a federal university of southern Brazil. First, students answered a questionnaire that aimed to establish the profile of these learners in the use of language and technology. Data collection took place over 6 classes in the computer lab, where students did reading discussion collaborative tasks in English in a chat tool with the mediation of the PA. After the assignments, students responded to questionnaires that sought to investigate their perceptions of the role and use of the PA in carrying out the tasks and in their learning. The task interactions, the use of the PA's functions and the data from the questionnaires were analyzed in search of the PA's mediation on students' learning and motivation. With these results, the present study was intended to contribute to the field of Computers in Education for the research on the impact of PAs in FL learning, suggesting solutions to improve Computer Supported Education. In the area of SL/FL acquisition, this study aimed to bring new data on studies of collaborative tasks by investigating the interaction with the PA as a new element for computer-mediated communication in language learning.

Esta é uma pesquisa quanti-qualitativa de estudo de caso que parte de princípios da teoria sociocultural aplicada à área de Aquisição de Segunda Língua (SL) e Língua Estrangeira (LE) e estudos de Informática na Educação a fim de investigar os efeitos da mediação de um agente pedagógico (AP) com estratégias de mediação específicas na aprendizagem colaborativa de inglês como LE em um ambiente virtual. A partir do aporte teórico desenvolvido, a metodologia desta pesquisa envolveu não só a elaboração e a aplicação de uma sequência de atividades de uso da tecnologia em tarefas colaborativas, mas, principalmente, no desenvolvimento de uma ferramenta AP integrado a uma ferramenta de mineração textual capaz de fazer intervenções nas discussões de textos em língua inglesa em uma sala de bate-papo. O contexto da pesquisa constituiu-se de uma turma de 25 estudantes de graduação em Letras/Inglês de uma universidade federal da região sul do Brasil. Primeiramente, os alunos responderam a um questionário que visou estabelecer o perfil desses aprendizes quanto ao uso da língua e da tecnologia. A coleta de dados se deu durante 6 encontros no laboratório de informática, em que os aprendizes realizaram em grupos 5 tarefas colaborativas de discussão de textos com a mediação do AP. Após as tarefas, os alunos responderam a questionários que buscaram investigar a sua percepção sobre o uso do AP na realização das tarefas e em sua aprendizagem. As interações, o uso das funções do AP e os dados dos questionários foram analisados em busca de indícios da mediação do AP no processo de aprendizagem. Com esses resultados, buscou-se contribuir na área de Informática na Educação para a pesquisa sobre o impacto de agentes pedagógicos na aprendizagem de línguas estrangeiras, sugerindo soluções para melhorar a educação apoiada por computador. Na área de Aquisição de SL/LE, pretendeu-se, ainda, trazer novos dados sobre estudos de tarefas colaborativas através da investigação da interação com o AP como um novo elemento para a comunicação mediada por computador na aprendizagem de línguas. / This is a quanti-litative case study that parts of theory sociocultural principles applied to Second Language (SL) and Foreign Language (FL) Acquisition and studies in Computers in Education in order to investigate the effects of a pedagogical agent's (PA) mediation with specific mediation strategies in English as a foreign language (EFL) collaborative learning in a virtual environment. From the theoretical framework developed, the methodology of this research involved not only the development and application of a sequence of activities using technology in EFL collaborative tasks, but mainly in the development of a PA integrated into a textual mining tool capable of doing interventions in reading discussions in a chat room. The context of the research consisted of a class of 25 graduate students in English Language and Literature in a federal university of southern Brazil. First, students answered a questionnaire that aimed to establish the profile of these learners in the use of language and technology. Data collection took place over 6 classes in the computer lab, where students did reading discussion collaborative tasks in English in a chat tool with the mediation of the PA. After the assignments, students responded to questionnaires that sought to investigate their perceptions of the role and use of the PA in carrying out the tasks and in their learning. The task interactions, the use of the PA's functions and the data from the questionnaires were analyzed in search of the PA's mediation on students' learning and motivation. With these results, the present study was intended to contribute to the field of Computers in Education for the research on the impact of PAs in FL learning, suggesting solutions to improve Computer Supported Education. In the area of SL/FL acquisition, this study aimed to bring new data on studies of collaborative tasks by investigating the interaction with the PA as a new element for computer-mediated communication in language learning.

Esta é uma pesquisa quanti-qualitativa de estudo de caso que parte de princípios da teoria sociocultural aplicada à área de Aquisição de Segunda Língua (SL) e Língua Estrangeira (LE) e estudos de Informática na Educação a fim de investigar os efeitos da mediação de um agente pedagógico (AP) com estratégias de mediação específicas na aprendizagem colaborativa de inglês como LE em um ambiente virtual. A partir do aporte teórico desenvolvido, a metodologia desta pesquisa envolveu não só a elaboração e a aplicação de uma sequência de atividades de uso da tecnologia em tarefas colaborativas, mas, principalmente, no desenvolvimento de uma ferramenta AP integrado a uma ferramenta de mineração textual capaz de fazer intervenções nas discussões de textos em língua inglesa em uma sala de bate-papo. O contexto da pesquisa constituiu-se de uma turma de 25 estudantes de graduação em Letras/Inglês de uma universidade federal da região sul do Brasil. Primeiramente, os alunos responderam a um questionário que visou estabelecer o perfil desses aprendizes quanto ao uso da língua e da tecnologia. A coleta de dados se deu durante 6 encontros no laboratório de informática, em que os aprendizes realizaram em grupos 5 tarefas colaborativas de discussão de textos com a mediação do AP. Após as tarefas, os alunos responderam a questionários que buscaram investigar a sua percepção sobre o uso do AP na realização das tarefas e em sua aprendizagem. As interações, o uso das funções do AP e os dados dos questionários foram analisados em busca de indícios da mediação do AP no processo de aprendizagem. Com esses resultados, buscou-se contribuir na área de Informática na Educação para a pesquisa sobre o impacto de agentes pedagógicos na aprendizagem de línguas estrangeiras, sugerindo soluções para melhorar a educação apoiada por computador. Na área de Aquisição de SL/LE, pretendeu-se, ainda, trazer novos dados sobre estudos de tarefas colaborativas através da investigação da interação com o AP como um novo elemento para a comunicação mediada por computador na aprendizagem de línguas. / This is a quanti-litative case study that parts of theory sociocultural principles applied to Second Language (SL) and Foreign Language (FL) Acquisition and studies in Computers in Education in order to investigate the effects of a pedagogical agent's (PA) mediation with specific mediation strategies in English as a foreign language (EFL) collaborative learning in a virtual environment. From the theoretical framework developed, the methodology of this research involved not only the development and application of a sequence of activities using technology in EFL collaborative tasks, but mainly in the development of a PA integrated into a textual mining tool capable of doing interventions in reading discussions in a chat room. The context of the research consisted of a class of 25 graduate students in English Language and Literature in a federal university of southern Brazil. First, students answered a questionnaire that aimed to establish the profile of these learners in the use of language and technology. Data collection took place over 6 classes in the computer lab, where students did reading discussion collaborative tasks in English in a chat tool with the mediation of the PA. After the assignments, students responded to questionnaires that sought to investigate their perceptions of the role and use of the PA in carrying out the tasks and in their learning. The task interactions, the use of the PA's functions and the data from the questionnaires were analyzed in search of the PA's mediation on students' learning and motivation. With these results, the present study was intended to contribute to the field of Computers in Education for the research on the impact of PAs in FL learning, suggesting solutions to improve Computer Supported Education. In the area of SL/FL acquisition, this study aimed to bring new data on studies of collaborative tasks by investigating the interaction with the PA as a new element for computer-mediated communication in language learning.

Dans cette thèse, nous présentons MEMORIA, un modèle de représentation de la mémoire de l’apprenant pour les systèmes tutoriels intelligents et adaptatifs. La contribution principale de ce modèle est une formalisation et une implémentation du modèle de l’apprenant sous forme de mémoires qui stockent les informations perçues par l’apprenant dans un environnement virtuel et les instructions émises par le tuteur. La conception de notre modèle est basée sur les quatre composantes classiques d’un système tutoriel intelligent. Le modèle du domaine est représenté par les connaissances métiers formalisées à l'aide de MASCARET. Afin de rendre naturelles les interactions entre le tuteur et l'apprenant, nous représentons le modèle de l'interface par l'intermédiaire d'un agent conversationnel animé à l'aide de la plate-forme Greta. Le modèle de l'apprenant est constitué de l'ensemble des connaissances acquises par l'apprenant en cours de simulation. Ces connaissances sont organisées dans trois mémoires : la mémoire sensorielle, la mémoire de travail et la mémoire à long terme. Notre enjeu majeur porte sur la formalisation de l'encodage des informations dans ces mémoires, ainsi que le flux de données entre celles-ci. Cette formalisation est basée sur la théorie de la mémoire humaine proposée par Atkinson et Shiffrin et inspirée de l'architecture cognitive ACT-R. Le modèle de tuteur que nous proposons est centré sur la réalisation d'un comportement qui adapte l'exécution du scénario en fonction des connaissances de l'apprenant et de ses interactions avec le tuteur. Une étude expérimentale a été menée pour valider notre modèle. Nous avons comparé deux groupes de participants. Dans le premier groupe, nous avons intégré un tuteur adaptatif utilisant notre modèle, qui adapte l'exécution du scénario pédagogique et dans le second groupe, un tuteur non adaptatif qui réalise un scénario pédagogique figé. Les résultats de cette étude permettent de conclure quant à l'efficacité de notre modèle pour un apprentissage de procédure. / In this thesis, we present MEMORIA, a model of the learner’s memory representation for adaptive and intelligent tutoring systems. The main contribution of this model is a formalization and an implementation of the learner's model using memories that store the information perceived by the learner in a virtual environment and the instructions given by the tutor. The design of our model is based on the four classic components of an intelligent tutorial system.The domain model is represented by the domain knowledge that is formalized using MASCARET. In order to make the interactions between the tutor and the learner natural, we represent the interface model through an embodied conversational agent using GRETA. The learner's model is made of all the knowledge acquired by the learner during the simulation. This knowledge is organized into three memories: sensory memory, working memory, and long-term memory. Our major challenge is to formalize the encoding of information in these memories, as well as the data flow between them.This formalization is based on the theory of human memory proposed by Atkinson and Shiffrin and inspired by the cognitive architecture ACT-R. Our proposed tutor model focuses on the realization of a behavior that adapts the execution of the pedagogical scenario according to the learner's knowledge and the interactions with the tutor. An experimental study was conducted to validate our model. We compared two groups of participants. In the first group, we integrated an adaptive tutor using our model which adapts the execution of the pedagogical scenario and in the second group, a non-adaptive tutor who applied a fixed pedagogical scenario. The results of this study allow us to conclude on the effectiveness of our model for procedural learning.