Die Visualisierung von Lernerdaten spielt in der online-gestützten Hochschullehre eine große Rolle. Durch Learning-Analytics-Ansätze kann problematisches Gruppen und Einzelverhalten frühzeitig diagnostiziert werden. Durch die Rückspiegelung lernrelevanter Daten und Informationen können beispielsweise Studierende im Online-Studium unterstützt (Krämer et al., 2017; Diziol et al., 2010) und die Leistung von Lerngruppen verglichen werden (Gaaw et al., 2017, S. 151). Um diese – häufig komplexen und vielschichtigen – Datensätze für Lernende zugänglich, erfassbar und kommunizierbar zu machen, sind geeignete Visualisierungsformen erforderlich. Im vorliegenden Beitrag wurden unterschiedliche Visualisierungsformen hinsichtlich der User Experience (UX), Ästhetik und des Gesamteindrucks mittels einer Online-Studie untersucht. [Aus der Einleitung.]

abstract: Learning analytics application is evolving into a student-facing solution. Student-facing learning analytics dashboards (SFLADs), as one popular application, occupies a pivotal position in online learning. However, the application of SFLADs faces challenges due to teacher-centered and researcher-centered approaches. The majority of SFLADs report student learning data to teachers, administrators, and researchers without direct student involvement in the design of SFLADs. The primary design criteria of SFLADs is developing interactive and user-friendly interfaces or sophisticated algorithms that analyze the collected data about students’ learning activities in various online environments. However, if students are not using these tools, then analytics about students are not useful. In response to this challenge, this study focuses on investigating student perceptions regarding the design of SFLADs aimed at providing ownership over learning. The study adopts an approach to design-based research (DBR; Barab, 2014) called the Integrative Learning Design Framework (ILDF; Bannan-Ritland, 2003). The theoretical conjectures and the definition of student ownership are both framed by Self-determination theory (SDT), including four concepts of academic motivation. There are two parts of the design in this study, including prototypes design and intervention design. They are guided by a general theory-based inference which is student ownership will improve student perceptions of learning in an autonomy-supportive SFLAD context. A semi-structured interview is used to gather student perceptions regarding the design of SFLADs aimed at providing ownership over learning. / Dissertation/Thesis / Masters Thesis Educational Psychology 2019

With globally increased migration and mobility between countries, it has become critical for many people to learn to speak a second language. The focus of this study is on adult migrant language learners that are learning a second language of the host country on the side of their working life. This study aims to support learners in their second language acquisition outside classrooms settings. In particular, it explores how the use of a specially designed application aimed at helping learners to keep track on how much time they spend on studying a second language affects their engagement and motivation to continue study the target language. To support migrant learners keeping track of the time spent on language learning activities (e.g., speaking, writing, reading and listening), a web-based application, the TimeTracker App, accessible through users’ mobile device has been developed by the researcher and offered to the learners. Participants in this study used the application for around two weeks. A mixed method approach was employed: data was collected through semi-structured interviews and by extracting log data from the application’s database. Interview data was analysed by means of a conventional content analysis and log data by using descriptive statistics. Overall, the study’s results show that the use of the TimeTracker App enabled the respondents to feel more aware of how much time they spent on their studies, and inspired them to devote more time to study the target language compared to before using the application. The findings suggest that migrant learners become more motivated and engaged in their second language learning when using the application. / Globalt ökad migration och rörlighet mellan länder har gjort det kritiskt för många att lära sig att tala ett andraspråk. Denna studie fokuserar på arbetande migranter som lär sig ett andraspråk vid sidan av sitt arbetsliv. Studien syftar till att stödja de studerande i sitt lärande av ett andraspråk utanför klassrummet. I synnerhet undersöker den hur användningen av en speciellt utformad applikation som syftar till att hjälpa eleverna att hålla reda på hur mycket tid de spenderar på att studera ett andraspråk påverkar deras engagemang och motivation för att fortsätta studera målspråket. För att hjälpa studerande migranter hålla reda på den tid som spenderas på språkinlärning (t ex att tala, skriva, läsa och lyssna) har en webbaserad applikation, TimeTracker App, som är tillgänglig via användarnas mobiltelefon, utvecklats av författaren och erbjudits till eleverna. Deltagarna i denna studie använde applikationen i cirka två veckor. En blandad metod användes: data samlades in genom halvstrukturerade intervjuer och genom att extrahera loggdata från applikationsdatabasen. Intervjudata analyserades med hjälp av en konventionell innehållsanalys och loggdata med hjälp av beskrivande statistik. Sammantaget visar studiens resultat att användningen av TimeTracker App gjorde det möjligt för respondenterna att bli mer medvetna om hur mycket tid de spenderade på sina studier och det inspirerade dem att ägna mer tid att studera målspråket jämfört med innan man använde applikationen. Resultaten tyder på att arbetande migranter blir mer motiverade och engagerade i sitt studerande av ett andraspråk när de använder applikationen.

[pt] Cursos online têm ampliado as possibilidades de pesquisa sobre comportamento e performance de estudantes. Esta tese investiga como apoiar instrutores na análise de logs de estudantes em Ambientes Virtuais de Aprendizagem. Primeiro, conduzimos entrevistas com instrutores e realizamos um mapeamento sistemático do estado da arte sobre Education Data Mining e Learning Analytics. Em seguida, analisamos logs de cursos online oferecidos no Brasil e comparamos nossas descobertas com resultados apresentados na literatura. Além disso, capturamos as preferências dos instrutores em relação a visualização de comportamento e performance de estudantes. Contudo, notamos uma lacuna de trabalhos mostrando modelos para o desenvolvimento de ferramentas de Learning Analytics. Com base nesses estudos, esta tese apresenta um modelo conectando teorias e modelos de visualização, assim como requisitos dos instrutores, suas preferências de visualização, diretrizes da literatura e métodos para análise de logs dos estudantes. Instanciamos e avaliamos esse modelo em uma ferramenta para montar dashboards, capturamos evidências de aceitação da nossa proposta e obtivemos feedbacks dos instrutores sobre a ferramenta tais como suas preferências de análise e visualizações. Por fim, apresentamos algumas considerações e discutimos lacunas existentes no trabalho que podem fundamentar e guiar futuras pesquisas, tais como desenvolvimento de novas instâncias e implantações do nosso modelo em instituições de ensino brasileiras e avaliação de eventuais mudanças na performance dos estudantes quando instrutores visualizam informações sobre o comportamento e performance deles, e agem de acordo. É importante ressaltar que a maioria dos estudos apresentados nessa tese foram conduzidos antes da pandemia de COVID-19. Somente o último estudo foi executado no início da pandemia no Brasil. / [en] Online education has broadened the avenues of research on student s behavior and performance. In this thesis, we shed light on how to support instructors in analyzing student logs from Virtual Learning Environments. Firstly, we conducted interviews with instructors and a systematic mapping of the state-of-art about Education Data Mining and Learning Analytics. Then, we analyzed logs from online courses offered in Brazil and compared our findings with results presented in the literature. Moreover, we gathered instructors preferences in regard to visualization of both students behavior and performance. However, we noted a lack of work showing models to support the development of learning analytics tools. In order to bridge this gap, this thesis presents a model connecting both Visual Analytics theories and models as well as instructors requirements, their visualization preferences, literature guidelines and methods for analyzing student logs. We instantiated and evaluated this model in a tool to assemble dashboards. We captured evidence of their acceptance of our proposal and obtained instructors feedback about the tool such as their both analysis and visualization preferences. Finally, we present some considerations and discuss gaps in existing works that can ground and guide future research, such as new instances of our model, as well as deploying them at Brazilian institutions and evaluating whether there are changes in students performance when instructors are able to see information about their behavior and performance, and act accordingly. It is worth highlighting that the majority of studies presented in this thesis were conducted before the COVID-19 pandemic. Only the last study was performed in the beginning of the pandemic in Brazil.

De Förenta Nationernas Agenda 2030 fastställer som ett delmål att säkerställa utbildning av hög kvalitet och främja livslångt lärande för alla som en del av arbetet för ett mer hållbart samhälle. Vikten av detta delmål blir särskilt tydlig i och med det observerbara sambandet mellan en fullständig gymnasieexamen och allmän hälsa i Sverige; gymnasiestudenter som går ut med en gymnasieexamen tenderar att erhålla bättre allmän hälsa. Learning Analytics är ett relativt nytt område inom utbildningsvetenskaplig forskning som syftar till att förbättra utbildning med hjälp av elevdata. Detta arbete undersökte vilken möjlig påverkan och begränsningar som förekommer vid implementering av en multipel linjär regressionsmodell utvecklad för en matematikkurs i en gymnasieskola. Vid utvecklingen av denna modell fastställdes tre signifikanta indikatorer för att förutsäga elevernas slutbetyg; Diagnos resultat,resultat på nationella proven och frånvaro. Prognosmodellen har utvärderats statistiskt varpå den visade sig vara tillförlitlig i 90% av bedömningarna, vilket inte är tillräckligt säkert för att användas i verkliga bedömningstillfällen eftersom lärare kräver att resultaten är obestridliga. Genom en fokusgruppsintervju med lärare granskas dessa resultat och deltagarna uttrycker sitt intresse för prognosmodeller tillsammans med en reflektion över elevers potentiella negativa reaktioner på en ogynnsam prognos. Utvärdering av modellen visar att den i dagsläget har en rimlig förmåga att förutsäga elevers slutbetyg men att det finns ett starkt behov av insamling av mer nyanserade data för att öka möjligheten till innovation i framtida arbeten / The 2030 Agenda establishes the goal to ensure quality education and promote lifelong learning opportunities for all. The importance of this goal becomes particularly clear when taking into account the link between upper secondary school graduation and general health in Sweden; Upper secondary school graduates tend to have better general health. Learning Analytics is a relatively new area of education research which aims to improve education using student data. This report examines the possible impact and limitations when implementing a multiple linear regression model developed for a mathematics course in an upper secondary school. In developing this model, three major indicators are established to be significant in predicting students' final grade; Diagnosis results, national test results and the amount of student absence. The model was statistically evaluated and found to be reliable in 90% of cases, which is not secure enough to be used in real assessment situations as teachers require the results to be indisputable. Through a focus group interview with teachers these results are evaluated and the participants establish their interest in predictive tools along with concerns for students' negative reactions to poor results. Evaluation of the model shows it has a reasonable ability to anticipate students' final grades but with a strong need for improvement in data collection methods and acquisition of more nuanced data to support greater possibility for innovation in future works.

In dieser Arbeit zeige ich in einem groß angelegten Experiment die Auswirkungen adaptiver Elemente in einer Online-Lernplattform. Ich werde darauf eingehen, dass die derzeitige Forschung zu Online-Lernplattformen für den L1-Erwerb hauptsächlich deskriptiv ist und dass nur wenige adaptive Lernumgebungen in der Praxis verbreitet sind. In dieser Dissertation werde ich ein Konzept entwickeln, wie adaptives Lernen in L1-Online-Lernplattformen integriert werden kann, und analysieren, ob dies zu verbesserten Lernerfahrungen führt. Dabei konzentriere ich mich auf die Effektivität und Fairness von Vorhersagen und Interventionen sowie auf die geeignete Softwarearchitektur für den Einsatz in der Praxis. Zunächst werden verschiedene Vorhersagemodelle entwickelt, die besonders in Blended-Learning-Szenarien nützlich sind. Anschließend entwickle ich ein Architekturkonzept (adaptive learning as a service), um bestehende Lernplattformen mithilfe von Microservices in adaptive Lernplattformen umzuwandeln. Darauf aufbauend wird ein groß angelegtes online-kontrolliertes Experiment mit mehr als 11.000 Nutzer*innen und mehr als 950.000 eingereichten Rechtschreibaufgaben durchgeführt. In einer abschließenden Studie werden die Vorhersagemodelle auf ihren algorithmischen Bias hin untersucht. Außerdem teste ich verschiedene Techniken zur Verringerung von Bias. Diese Arbeit bietet eine ganzheitliche Sicht auf das adaptive Lernen beim Online-L1-Lernen. Durch die Untersuchung mehrerer Schlüsselaspekte (Vorhersagemodelle, Interventionen, Architektur und Fairness) ermöglicht die Arbeit Schlussfolgerungen sowohl für die Forschung als auch für die Praxis. / In this work I show in a large scale experiment the effect of adding adaptive elements to an online learning platform. I will discuss that the current research on online learning platforms in L1 acquisition is mainly descriptive and that only few adaptive learning environments are prevalent in practice. In this dissertation, I will develop a concept on how to integrate adaptive L1 online learning and analyse if it leads to improved learning experiences. I focus on the effectiveness and fairness of predictions and interventions as well as on the suitable software architecture for use in practice. First, I develop different prediction models, which are particularly useful in blended classroom scenarios. Subsequently, I develop an architectural concept (adaptive learning as a service) to transform existing learning platforms into adaptive learning platforms using microservices. Based on this, a large-scale online-controlled experiment with more than 11,000 users and more than 950,000 submitted spelling tasks is carried out. In the final study, the prediction models are examined for their algorithmic bias, by comparing different machine learning models, varying metrics of fairness, and multiple demographic categories. Furthermore, I test various bias mitigation techniques. The success of bias mitigation approaches depends on the demographic group and metric. However, in-process methods have proven to be particularly successful. This work provides a holistic view of adaptive learning in online L1 learning. By examining several key aspects (predictive models, interventions, architecture, and fairness), the work allows conclusions to be drawn for both research and practice.

Previous research suggests that the optimal time of day (TOD) for cognitive function for young adults occurs in the afternoon and evening times (Allen, et al. 2008; May, et al. 1993). The implication is college students may be more successful if they schedule classes and tests in the afternoon and evening times, but in asynchronous learning environments, “class” and tests take place at any TOD (or night) a student might choose. The problem is that there may be a disadvantage for students choosing to take tests at certain TOD. As educators, we need to be aware of potential barriers to student success and be prepared to offer guidance to students. This research study found a significant negative correlation between TOD and assessment scores on tests taken between 16:01 and 22:00 hours as measured in military time. While this study shows that academic performance on asynchronous assessments was high at 16:00 hours, student performance diminished significantly by 22:00 hours. When efforts were taken to mitigate the extraneous variables related to test complexity and individual academic achievement, the effect TOD had on assessment achievement during this time period was comparable to the effect of test complexity on that achievement. However, when analyzed using a small sub-set of the data neither GPA nor TOD could be used to predict student scores on tests taken between 16:01 and 22:00 hours. Finally, individual circadian arousal types (evening, morning and neutral) (Horne & Ostberg, 1976) and actual TOD students took tests were analyzed to determine if synchrony, the match between circadian arousal type and peak cognitive performance, existed. The synchrony effect could not be confirmed among morning type students taking this asynchronous online course, but evidence suggests that synchrony could have contributed to student success for evening types taking this asynchronous online courses. The implication of this study is that online instructors, instructional designers and students should consider TOD as a factor affecting achievement in asynchronous online courses. Results of this research are intended to propose further research into TOD effects in asynchronous online settings, and to offer guidance to online students as well as online instructors and instructional designers faced with setting deadlines and advising students on how to be successful when learning online.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第23315号 / 情博第751号 / 新制||情||128(附属図書館) / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 緒方 広明, 教授 黒田 知宏, 教授 楠見 孝 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Student affect can play a profoundly important role in students' post-school lives. Understanding students' affective states within online learning environments in particular has become an important matter of research, as digital tutoring systems have the potential to intervene at the moment that students are struggling and becoming frustrated, bored or disengaged. However, despite the importance of assessing students' affective states, there is no clear consensus about what emotions are most important to assess, nor how these emotions can be best measured. This dissertation investigates students’ self-reports of their emotions and causal attributions of those emotions collected while they are solving math problems within a mathematics tutoring system. These self-reports are collected in two conditions: through limited choice Likert response and through open response text boxes. The conditions are combined with students’ cognitive attributions to describe epistemic (neither purely affective nor purely cognitive) emotions in order to explain the relationship between observable student behaviors in the MathSpring.org tutoring system and student affect. These factors include beliefs, expectations, motivations, and perceptions of ability and control. A special emphasis of this dissertation is on analyzing the role of causal attributions for the events and appraisals of the learning environment, as possible causes of student behaviors, performance, and affect.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2016-04-13T15:28:01Z No. of bitstreams: 1 João Luiz Cavalcante Ferreira_.pdf: 1672669 bytes, checksum: 80b5c6fbc873c9f858b230e78855dd55 (MD5) / Made available in DSpace on 2016-04-13T15:28:01Z (GMT). No. of bitstreams: 1 João Luiz Cavalcante Ferreira_.pdf: 1672669 bytes, checksum: 80b5c6fbc873c9f858b230e78855dd55 (MD5) Previous issue date: 2016-02-25 / Nenhuma / A Educação a Distância (EaD) no Brasil tem se consolidado com diversos estudantes optando por essa modalidade de ensino para ampliar suas formações e realização profissional, no entanto ela enfrenta alguns obstáculos, como a resistência de educandos e educadores, desafios organizacionais, custos de produção e a questão da reprovação ou retenção de alunos. Um dos principais diferenciais dos cursos EaD é a grande quantidade de dados gerados pelas interações no ambiente educacional, o que abre novas possibilidades para estudar e compreender estas interações. A Mineração de Dados educacionais (MDE) é uma área de pesquisa interdisciplinar que lida com o desenvolvimento de métodos para explorar dados originados no contexto educacional. A Learning Analytics (LA) é outra área de pesquisa emergente. Ela busca medir, coletar, analisar e relatar dados sobre estudantes. O desafio dos pesquisadores é desenvolver métodos capazes de prever o desempenho dos estudantes de modo a possibilitar a intervenção de professores e tutores visando resgatar o estudante antes que reprove. Esta dissertação propõe o MD-PREAD, um modelo para predição de grupos de risco de reprovação em um ambiente de Educação a Distância. A técnica de árvore de decisão foi utilizada para possibilitar um diferencial quanto à possibilidade de interpretação dos dados gerados pelo uso dos métodos de predição, pois outros métodos, tais como Redes Neurais Artificiais possuem como deficiência justamente a dificuldade de identificar as causas que levam aos resultados das predições. O modelo foi prototipado na ferramenta de mineração RapidMiner. Um experimento foi realizado no Instituto Federal de Educação, Ciência e Tecnologia do Amazonas, no programa Universidade Aberta do Brasil, no Curso de Filosofia da educação. Foram feitas coletas de dados históricos de 10 disciplinas de um grupo de 30 aprendizes em dois semestres consecutivos, 2014/2 e 2015/1, o total de alunos matriculados foi de 125, o total de interações levantadas foi de 41070, o cálculo de predição considerou as médias das avaliações de 30 aprendizes, os desvios padrões das interações e suas respectivas situações. Estes dados serviram para compor o conjunto de treinamento necessário para a definição da regra de classificação que teve como predominante a acurácia de 55% e a confiabilidade Kappa de 0,22. Foi realizado um segundo processo de validação, após o experimento, considerou-se os 125 alunos e o melhor classificador encontrado foi o J48 com a acurácia de 84,05%, precisão de 77,08% e recall de 50,23%. Concluiu-se que o MD-PREAD é uma ferramenta de auxílio no prognóstico de grupos de risco de reprovação, uma vez que possibilitou a geração e disponibilização semanal destes grupos a um sistema de recomendação educacional externo. / E-learning in Brazil has been established with many students opting for this type of education to expand their training and professional achievement, however it faces some obstacles, such as resistance from students and educators, organizational challenges, production costs and the question of failure or retention of students. One of the main advantages of e-learning courses is the large amount of data generated by the interactions in the educational environment, which opens up new possibilities to study and understand these interactions. Educational Data Mining (EDM) is an area of interdisciplinary research that deals with the development of methods to explore data that originates in the educational context. Learning Analytics (LA) is another area of emerging research. It seeks to measure, collect, analyze and report data on students. The challenge for researchers is to develop methods to predict the performance of students in order to allow the intervention of teachers and tutors aiming to retrieve the student before failing. This thesis proposes the MD-PREAD, a model for predicting failure of risk groups in a e-learning environment. The decision tree technique was used to enable a difference as to whether the interpretation of the data generated by the use of prediction methods, since other methods such as Artificial Neural Networks that has as disability difficulty in identifying precisely the causes that lead to predictions results. The model was prototyped in RapidMiner mining tool. An experiment was conducted at the Federal Institute of Education, Science and Technology of Amazonas, the Open University of Brazil program in course Philosophy of education. Historical data collection of 10 disciplines from a group of 30 apprentices were made in two consecutive semesters, 2014/2 and 2015/1, the total number of enrolled students was 125, the total raised interactions were 41070, the prediction calculation considered average of 30 apprentices ratings, the standard deviations of the interactions and their situations. These data served to compose the training set required for classification rule defining which had as predominant accuracy of 55% and Kappa reliability 0.22. A second validation process was carried out after the experiment. It was considered the total amount of 125 apprentices and the best classifier found was the J48 with the accuracy of 84.05%, 77.08% of classification precision and recall of 50.23%. It was concluded that the MD-PREAD is a support tool in the prognosis of failure risk groups, since it enabled the generation and weekly availability of these groups to a recommendation system.