Learning analytics focuses on using existing accumulated learning data through analysis related techniques to provide appropriate information to learners and facilitating learners to adjust their learning strategies (personalization and adaptation) in improving learning effectiveness. Through learning analytics, activities of teaching, learning, and management processes will be significantly changed. Although learning analytics has been considered one of the six critical trends (ebook, mobile learning, augmented reality, game-based learning, natural user interface, and learning analytics) of high education in the near future, there are only few studies focusing on exploring learning analytics related issues. To address this void, this thesis aims for analyzing and designing a personalized mobile learning analytics system that is a mobile application prototyping system developed by incorporating concepts of learning analytics and mobile learning. User requirements of the prototyping system are collected by database analysis (LMS platform), focus groups (users of mobile learning), and expert interviews (experts and practitioners in e-learning domain). Those collected requirements have been translated into system functionalities and then they have been appropriately implemented through adequate system development tools. Finally, the implemented prototyping system has been tested and validated by experts and practitioners in e-learning domain. Therefore, this study has significant contributions on conducting an in-depth system analysis and design relating to mobile learning with learning analytics and validating the feasibility of learning analytics by the prototyping approach. We suggest that academics and practitioners can conduct more in-depth research on investigating learning analytics related issues based on the findings of this study.

This study investigated personalized adaptive learning, teacher education, and self-efficacy to determine if personalized adaptive teacher education can increase self-efficacy. It is suggested that teachers with higher self-efficacy tend to stay in the teaching profession longer. Chapters 2 and 3 are literature reviews on personalizing adaptive learning to determine what common components are used in personalized adaptive learning systems to get a clear understanding of what previous literature suggests building this study on it. Chapter 4 investigates the data collected from 385 teachers to understand better what teachers report on factors that increase their self-efficacy. As a result, it was found that teachers' self-efficacy increases with more training, support, and resources. In chapter 5, a framework was developed based on previous findings, with components of personalized adaptive learning to provide support/help at the right time for teachers to increase their self-efficacy. An empirical study was conducted to validate this framework, where the framework was used as a guide to personalize and adapt summer teacher preservice training and survey teachers on their self-efficacy before and after the training to see its impact on teachers' self-efficacy. However, since summer preservice training was virtual, the framework could not be implemented fully, as we were not able to observe teachers' behaviors and monitor their learning to provide them help and support, as needed and being in the post-COVID-19 year as educators dealing with about two-year learning loss systemwide, seems decreased teachers' self-efficacy. The findings of this study can guide preservice teacher education institutions and decision-makers of teacher education to assess inservice teachers' needs and self-efficacy to help and support them with a more personalized adaptive education to improve their self-efficacy.

Avec la quantité croissante du contenu pédagogique produit chaque jour par les utilisateurs, il devient très difficile pour les apprenants de trouver les ressources les plus adaptées à leurs besoins. Les systèmes de recommandation sont utilisés dans les plateformes éducatives pour résoudre le problème de surcharge d'information. Ils sont conçus pour fournir des ressources pertinentes à un apprenant en utilisant certaines informations sur les utilisateurs et les ressources. Le présent travail s'inscrit dans le contexte des systèmes de recommandation des ressources pédagogiques, en particulier les systèmes qui utilisent des informations sociales. Nous avons défini une approche de recommandation de ressources éducatives en se basant sur les résultats de recherche dans le domaine des systèmes de recommandation, des réseaux sociaux et des environnements informatiques pour l’apprentissage humain. Nous nous appuyons sur les relations sociales entre apprenants pour améliorer la précision des recommandations. Notre proposition est basée sur des modèles formels qui calculent la similarité entre les utilisateurs d'un environnement d'apprentissage pour générer trois types de recommandation, à savoir la recommandation des 1) ressources populaires, 2) ressources utiles et 3) ressources récemment consultées. Nous avons développé une plateforme d'apprentissage, appelée Icraa, qui intègre nos modèles de recommandation. La plateforme Icraa est un environnement d’apprentissage social qui permet aux apprenants de télécharger, de visualiser et d’évaluer les ressources éducatives. Dans cette thèse, nous présentons les résultats d'une expérimentation menée pendant deux ans qui a impliqué un groupe de 372 apprenants d'Icraa dans un contexte éducatif réel. L'objectif de cette expérimentation est de mesurer la pertinence, la qualité et l'utilité des ressources recommandées. Cette étude nous a permis d'analyser les retours des utilisateurs concernant les trois types de recommandations. Cette analyse a été basée sur les traces des utilisateurs enregistrées avec Icraa et sur un questionnaire. Nous avons également effectué une analyse hors ligne en utilisant un jeu de données afin de comparer notre approche avec quatre algorithmes de référence. / With the increasing amount of educational content produced daily by users, it becomes very difficult for learners to find the resources that are best suited to their needs. Recommendation systems are used in educational platforms to solve the problem of information overload. They are designed to provide relevant resources to a learner using some information about users and resources. The present work fits in the context of recommender systems for educational resources, especially systems that use social information. We have defined an educational resource recommendation approach based on research findings in the area of recommender systems, social networks, and Technology-Enhanced Learning. We rely on social relations between learners to improve the accuracy of recommendations. Our proposal is based on formal models that calculate the similarity between users of a learning environment to generate three types of recommendation, namely the recommendation of 1) popular resources; 2) useful resources; and 3) resources recently consulted. We have developed a learning platform, called Icraa, which integrates our recommendation models. The Icraa platform is a social learning environment that allows learners to download, view and evaluate educational resources. In this thesis, we present the results of an experiment conducted for almost two years on a group of 372 learners of Icraa in a real educational context. The objective of this experiment is to measure the relevance, quality and usefulness of the recommended resources. This study allowed us to analyze the user’s feedback on the three types of recommendations. This analysis is based on the users’ traces which was saved with Icraa and on a questionnaire. We have also performed an offline analysis using a dataset to compare our approach with four base line algorithms.

While it is difficult for base stations to estimate the millimeter wave (mmWave) channels and find the optimal mmWave beam for user equipments (UEs) quickly, the sub-6 GHz channels which are usually easier to obtain and more robust to blockages could be used to reduce the time before initial access and enhance the reliability of mmWave communication. Considering that the channel information is collected by a massive number of radio base stations and would be sensitive to privacy and security, Federated Learning (FL) is a match for this use case. In practice, the channel vectors are usually subject to Non-Independently Distributed (non-IID) distributions due to the greatly varying wireless communication environments between different radio base stations and their UEs. To achieve satisfying performance for all radio base stations instead of only the majority of them, a useful solution is designing personalized methods for each radio base station. In this thesis, we implement two personalized FL methods including 1) Finetuning FL Model on Private Dataset of Each Client and 2) Adaptive Expert Models for FL to predict the optimal mmWave beamforming vector directly from the non-IID sub-6 GHz channel vectors generated from DeepMIMO. According to our experimental results, Finetuning FL Model on Private Dataset of Each Client achieves higher average mmWave downlink spectral efficiency than the global FL. Besides, in terms of the average Top-1 and Top-3 classification accuracies, its performance improvement over the global FL model even exceeds the improvement of the global FL over the pure local models. / Även om det är svårt för en basstation att uppskatta en kanal för millimetervåg (mmWave) och snabbt hitta den bästa mmWave-strålen för en användarutrustning (UE), kan den dra fördel av kanaler under 6 GHz, som i allmänhet är mer lättillgängliga och mer motståndskraftig mot blockering, för att minska tid för första besök och förbättra tillförlitligheten hos mmWave-kommunikation. Med tanke på att kanalinformation samlas in av ett stort antal radiobasstationer och är känslig för integritet och säkerhet är federated learning (FL) väl lämpat för detta användningsfall. I praktiken, eftersom den trådlösa kommunikationsmiljön varierar mycket mellan olika radiobasstationer och deras UE, följer kanalvektorer vanligtvis en icke-oberoende distribution (icke-IID). För att uppnå tillfredsställande prestanda för alla radiobasstationer, inte bara de flesta radiobasstationer, är en användbar lösning att utforma ett individuellt tillvägagångssätt för varje radiobasstation. I detta dokument implementerar vi två personliga FL-metoder, inklusive 1) finjustering av FL-modellen på varje klients privata datauppsättning och 2) en adaptiv expertmodell av FL för att direkt generera icke-IID sub-6 GHz kanalvektorer förutsäga optimal mmWave beamforming vektorer. Enligt våra experimentella resultat uppnår finjustering av FL-modellen på varje klients privata datauppsättning högre genomsnittlig mmWave-nedlänksspektral effektivitet än global FL. Dessutom överträffar dess prestandaförbättring jämfört med den globala FL-modellen till och med den för den globala FL jämfört med den rent lokala modellen vad gäller genomsnittlig klassificeringsnoggrannhet i topp-1 och topp-3.

Enrollment in online courses is increasing at a much higher rate than enrollment in on campus courses. Initially, online systems were developed by moving course content from in-class courses as is to an online platform. Later, Web 2.0 technology was implemented in order to improve students’ online engagement. These systems considered all students as one homogeneous group and ignored the fact that different students learn in different ways and at different speeds. Later, adaptive online learning systems were developed based on the assumption that if the instructional approach matches the student learning style, student performance and experience will improve. The use of these systems yielded mixed results because there is no agreement on what, how, and when to adapt instructions. The problem is that there is still a lack of empirical evidence about which online learning system’ design is the most effective, efficient, and engaging. There were two goals for this study. The first was to develop a new instructional theory and design model suitable for personalizing and adapting online learning. The first goal was achieved by developing student personalized, adaptive, and comprehensive e-learning spaces instructional theory and design model. This theory is based on finding the best fit among student characteristics, knowledge domain objectives, and technology used in delivering the online course. The second goal was to implement the newly developed theory and design model in an e-learning system prototype. This goal was achieved by developing and internally validating the e-learning system prototype by utilizing a panel of five instructional design experts. The Delphi method was used to solicit input from the expert panel in three rounds of validation. The validation process resulted in the experts’ consensus that the prototype incorporated the instructional theory and design model well and that this instructional theory holds the promise of increasing online learning courses’ effectiveness, efficiency, and student engagement.

The recent release of AI tools for public use allows for the development of novel teaching approaches for goals that often present challenges in the classroom, such as the need for personalized learning materials. The current study enlists a four-week ChatGPT-based personalized learning intervention in tandem with a teacher questionnaire and interviews in two upper-secondary schools in Southern Sweden to investigate English teacher perceptions of the benefits and challenges of using AI for personalized language learning. In addition, the intervention investigates the potential effectiveness of personalized learning assignments using ChatGPT on the development of students’ grammar abilities in a specific, local classroom context to both address a local need at the school in question and to serve as a proof of concept for more broad-based, future research on the use of these tools for this purpose. The questionnaire revealed that teachers initially had some concerns regarding the accuracy, reliability, and practical implementation of such tools. However, the intervention was found to significantly reduce grammar errors in student writing, and in follow-up interviews, teachers reported feeling more receptive to such approaches after interacting with the tools and seeing the beneficial results. These findings demonstrate that teachers may be hesitant to implement AI tools, which underscores the importance of training and first-hand use for promoting their successful adoption into pedagogical practices. In addition, the findings suggest that AI-based tools for personalized language learning may also be successful in a broader educational context. Finally, certain limitations, such as the small sample size, are acknowledged which emphasizes that further research is necessary to acquire a more comprehensive understanding of personalized learning using AI-based tools like ChatGPT.

Focusing on personalized grammar tasks, this study dives into the integration of Generative Artificial Intelligence into English as a Second Language education. By utilizing a mixed methods approach, incorporating both qualitative and quantitative analyses the study explores how personalized learning can be improved by employing ChatGPT. Results from the study indicate that GAI-driven personalization significantly enhances student engagement and motivation. This offers a promising path for tailoring education to individual learner needs toward a more inclusive classroom. A central outcome of this study is the proposal of a new theoretical framework the Personalization-Motivation Integration Framework (PMIF). This framework clarifies the synergistic effects of integrating content and topic personalization to significantly boost student motivation and reach a more inclusive learning environment. This adds to the growing research about AI's potential in education as it indicates that these technologies can significantly enhance teaching and offer a more tailored and inclusive learning environment.