Pub Date : 2025-01-15DOI: 10.1109/TLT.2025.3529994
Nicolas Pope;Juho Kahila;Henriikka Vartiainen;Matti Tedre
The rapid advancement of artificial intelligence and its increasing societal impacts have turned many computing educators' focus toward early education in machine learning (ML). Limited options for educational tools for teaching novice learners about the mechanisms of ML and data-driven systems presents a recognized challenge in K–12 computing education. In response, we introduce “GenAI Teachable Machine,” a visual, data-driven design platform aimed at introducing novice learners to fundamental ML concepts and workflows, particularly in the context of classifiers. Following the design science research (DSR) method, this study presents the prior recommendations, standards, codevelopment, and extensive field testing that resulted in a platform enabling young learners to express their own interest-driven ideas through codesigning and sharing personally meaningful apps. The platform improves on the design of Google's popular Teachable Machine 2 by its ability to create a standalone app by defining one or more actions to be triggered by each classifier result, and deploy that app to other devices. It also enables one to distribute the collection of training data among many users. In addition to the DSR process, this article presents findings from usability lab tests (N = 8) and 6-h classroom projects involving fourth and seventh grade children (N = 213). The results show that children who had no experience of ML were able to navigate through the workflow and turn their own ideas into concrete ML-based apps. The majority of children were able to reflect and present, in their own words, their working process using data-driven (design) thinking concepts and insights.
{"title":"Children's AI Design Platform for Making and Deploying ML-Driven Apps: Design, Testing, and Development","authors":"Nicolas Pope;Juho Kahila;Henriikka Vartiainen;Matti Tedre","doi":"10.1109/TLT.2025.3529994","DOIUrl":"https://doi.org/10.1109/TLT.2025.3529994","url":null,"abstract":"The rapid advancement of artificial intelligence and its increasing societal impacts have turned many computing educators' focus toward early education in machine learning (ML). Limited options for educational tools for teaching novice learners about the mechanisms of ML and data-driven systems presents a recognized challenge in K–12 computing education. In response, we introduce “GenAI Teachable Machine,” a visual, data-driven design platform aimed at introducing novice learners to fundamental ML concepts and workflows, particularly in the context of classifiers. Following the design science research (DSR) method, this study presents the prior recommendations, standards, codevelopment, and extensive field testing that resulted in a platform enabling young learners to express their own interest-driven ideas through codesigning and sharing personally meaningful apps. The platform improves on the design of Google's popular Teachable Machine 2 by its ability to create a standalone app by defining one or more actions to be triggered by each classifier result, and deploy that app to other devices. It also enables one to distribute the collection of training data among many users. In addition to the DSR process, this article presents findings from usability lab tests (<italic>N</i> = 8) and 6-h classroom projects involving fourth and seventh grade children (<italic>N</i> = 213). The results show that children who had no experience of ML were able to navigate through the workflow and turn their own ideas into concrete ML-based apps. The majority of children were able to reflect and present, in their own words, their working process using data-driven (design) thinking concepts and insights.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"130-144"},"PeriodicalIF":2.9,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10842355","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-10DOI: 10.1109/TLT.2025.3526863
Jamie I. Cross;Christine C. Boag-Hodgson
The incorporation of immersive technologies into student pilot training has been hindered by a lack of empirical evidence to support their efficacy. Existing research on virtual reality flight simulators is limited in scope, predominantly focused on single-users in small, piston-engine aircraft, with little concern for its application to commercial pilot operations. This article initiates the process of evaluating a virtual reality flight simulator to train ab-initio pilots in a multicrew environment using a complex jet aircraft (a Boeing 737-800). An experimental design-based research methodology was initially employed to identify and address any methodological issues. To demonstrate proof of concept, the study evaluated two different scenarios and assessed the performance of two head-mounted displays. Additionally, the research included measures of situational awareness and workload. The setup was configured to allow the evaluation of various combinations of virtual reality and desktop flight simulators within a multicrew environment. Valuable insights have been gained in creating a reliable environment for further research on collaborative virtual reality flight simulators. Proof of concept was demonstrated through satisfactory usability and fidelity in a two-pilot virtual reality simulator. The study confirmed that participants can effectively collaborate in a virtual environment during simulator sessions modeled on a typical initial First Officer airline training program for complex commercial aircraft. Participants in the virtual environment exhibited reduced workload (effort) in comparison to a desktop flight simulator, indicating a potential decrease in cognitive processing. This, in turn, suggests enhanced spatial memory, corroborated by measures of heightened team situational awareness in the virtual environment. The benefits of these findings are numerous, including the potential for a virtual reality flight simulator to supplement traditional pilot training methods.
{"title":"A Collaborative Virtual Reality Flight Simulator: Efficacy, Challenges, and Potential","authors":"Jamie I. Cross;Christine C. Boag-Hodgson","doi":"10.1109/TLT.2025.3526863","DOIUrl":"https://doi.org/10.1109/TLT.2025.3526863","url":null,"abstract":"The incorporation of immersive technologies into student pilot training has been hindered by a lack of empirical evidence to support their efficacy. Existing research on virtual reality flight simulators is limited in scope, predominantly focused on single-users in small, piston-engine aircraft, with little concern for its application to commercial pilot operations. This article initiates the process of evaluating a virtual reality flight simulator to train ab-initio pilots in a multicrew environment using a complex jet aircraft (a Boeing 737-800). An experimental design-based research methodology was initially employed to identify and address any methodological issues. To demonstrate proof of concept, the study evaluated two different scenarios and assessed the performance of two head-mounted displays. Additionally, the research included measures of situational awareness and workload. The setup was configured to allow the evaluation of various combinations of virtual reality and desktop flight simulators within a multicrew environment. Valuable insights have been gained in creating a reliable environment for further research on collaborative virtual reality flight simulators. Proof of concept was demonstrated through satisfactory usability and fidelity in a two-pilot virtual reality simulator. The study confirmed that participants can effectively collaborate in a virtual environment during simulator sessions modeled on a typical initial First Officer airline training program for complex commercial aircraft. Participants in the virtual environment exhibited reduced workload (effort) in comparison to a desktop flight simulator, indicating a potential decrease in cognitive processing. This, in turn, suggests enhanced spatial memory, corroborated by measures of heightened team situational awareness in the virtual environment. The benefits of these findings are numerous, including the potential for a virtual reality flight simulator to supplement traditional pilot training methods.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"119-129"},"PeriodicalIF":2.9,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Learning performance data, such as correct or incorrect answers and problem-solving attempts in intelligent tutoring systems (ITSs), facilitate the assessment of knowledge mastery and the delivery of effective instructions. However, these data tend to be highly sparse (80%$sim$90% missing observations) in most real-world applications. This data sparsity presents challenges to using learner models to effectively predict learners' future performance and explore new hypotheses about learning. This article proposes a systematic framework for augmenting learning performance data to address data sparsity. First, learning performance data can be represented as a 3-D tensor with dimensions corresponding to learners, questions, and attempts, effectively capturing longitudinal knowledge states during learning. Second, a tensor factorization method is used to impute missing values in sparse tensors of collected learner data, thereby grounding the imputation on knowledge tracing (KT) tasks that predict missing performance values based on real observations. Third, data augmentation using generative artificial intelligence models, including generative adversarial network (GAN), specifically vanilla GANs and generative pretrained transformers (GPTs, specifically GPT-4o), generate data tailored to individual clusters of learning performance. We tested this systemic framework on adult literacy datasets from AutoTutor lessons developed for adult reading comprehension. We found that tensor factorization outperformed baseline KT techniques in tracing and predicting learning performance, demonstrating higher fidelity in data imputation, and the vanilla GAN-based augmentation demonstrated greater overall stability across varying sample sizes, whereas GPT-4o-based augmentation exhibited higher variability, with occasional cases showing closer fidelity to the original data distribution. This framework facilitates the effective augmentation of learning performance data, enabling controlled, cost-effective approach for the evaluation and optimization of ITS instructional designs in both online and offline environments prior to deployment, and supporting advanced educational data mining and learning analytics.
{"title":"Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI","authors":"Liang Zhang;Jionghao Lin;John Sabatini;Conrad Borchers;Daniel Weitekamp;Meng Cao;John Hollander;Xiangen Hu;Arthur C. Graesser","doi":"10.1109/TLT.2025.3526582","DOIUrl":"https://doi.org/10.1109/TLT.2025.3526582","url":null,"abstract":"Learning performance data, such as correct or incorrect answers and problem-solving attempts in intelligent tutoring systems (ITSs), facilitate the assessment of knowledge mastery and the delivery of effective instructions. However, these data tend to be highly sparse (80%<inline-formula><tex-math>$sim$</tex-math></inline-formula>90% missing observations) in most real-world applications. This data sparsity presents challenges to using learner models to effectively predict learners' future performance and explore new hypotheses about learning. This article proposes a systematic framework for augmenting learning performance data to address data sparsity. First, learning performance data can be represented as a 3-D tensor with dimensions corresponding to learners, questions, and attempts, effectively capturing longitudinal knowledge states during learning. Second, a tensor factorization method is used to impute missing values in sparse tensors of collected learner data, thereby grounding the imputation on knowledge tracing (KT) tasks that predict missing performance values based on real observations. Third, data augmentation using generative artificial intelligence models, including generative adversarial network (GAN), specifically vanilla GANs and generative pretrained transformers (GPTs, specifically GPT-4o), generate data tailored to individual clusters of learning performance. We tested this systemic framework on adult literacy datasets from AutoTutor lessons developed for adult reading comprehension. We found that tensor factorization outperformed baseline KT techniques in tracing and predicting learning performance, demonstrating higher fidelity in data imputation, and the vanilla GAN-based augmentation demonstrated greater overall stability across varying sample sizes, whereas GPT-4o-based augmentation exhibited higher variability, with occasional cases showing closer fidelity to the original data distribution. This framework facilitates the effective augmentation of learning performance data, enabling controlled, cost-effective approach for the evaluation and optimization of ITS instructional designs in both online and offline environments prior to deployment, and supporting advanced educational data mining and learning analytics.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"145-164"},"PeriodicalIF":2.9,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-06DOI: 10.1109/TLT.2025.3525949
Malte Rolf Teichmann
Due to the rise of virtual reality and the—at least now—hypothetical construct of the Metaverse, learning processes are increasingly transferred to immersive virtual learning environments. While the literature provides few design guidelines, most papers miss an application and evaluation description of the design and development processes. As a result, few standardized design processes and related design frameworks exist that meaningfully integrate existing stand-alone design theories and resulting approaches for developing immersive virtual learning environments. The article tackles this challenge with a research procedure based on the design science research method to outline and communicate a Design process framework to create virtual learning environments based on real-world processes for the Edu-Metaverse. The simply applicable artifact represents a comprehensive five-step solution to a well-defined problem by combining interdisciplinary perspectives. It contributes to the concretization of the hypothetical term Metaverse in its intended domain. As a result, practitioners and researchers with different experience levels can use the low-threshold framework.
{"title":"How to Design Immersive Virtual Learning Environments Based on Real-World Processes for the Edu-Metaverse—A Design Process Framework","authors":"Malte Rolf Teichmann","doi":"10.1109/TLT.2025.3525949","DOIUrl":"https://doi.org/10.1109/TLT.2025.3525949","url":null,"abstract":"Due to the rise of virtual reality and the—at least now—hypothetical construct of the <italic>Metaverse</i>, learning processes are increasingly transferred to <italic>immersive virtual learning environments</i>. While the literature provides few design guidelines, most papers miss an application and evaluation description of the design and development processes. As a result, few standardized design processes and related design frameworks exist that meaningfully integrate existing stand-alone design theories and resulting approaches for developing <italic>immersive virtual learning environments</i>. The article tackles this challenge with a research procedure based on the design science research method to outline and communicate a <italic>Design process framework to create virtual learning environments based on real-world processes for the Edu-Metaverse</i>. The simply applicable artifact represents a comprehensive five-step solution to a well-defined problem by combining interdisciplinary perspectives. It contributes to the concretization of the hypothetical term <italic>Metaverse</i> in its intended domain. As a result, practitioners and researchers with different experience levels can use the low-threshold framework.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"100-118"},"PeriodicalIF":2.9,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10824930","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article introduces the development process of social presence-enabled augmented reality (SPEAR) tool, an innovative augmented reality (AR) based learning application tailored for online engineering education. SPEAR focuses on a learning module of structural beam-bending, empowering users to seamlessly integrate 3-D virtual beams into their real-world environment, using the AR Foundation framework within the Unity game engine. Learners can explore structural mechanics by manipulating loads and positions. SPEAR leverages a custom C# script based on the finite element method to offer a real-time simulation of beam deformation, accompanied by visualizations of the moment/shear diagrams and bending stresses. In addition, the integration of a cloud-based voice chat feature, photon unity networking 2, enhances social presence, fostering collaborative learning. Usability testing conducted with extended reality developers and structural engineers, utilizing the system usability scale, confirmed SPEAR's user-friendliness and intuitive interface. Results indicate high levels of participant satisfaction, validating its design and functionality. This study contributes to the field by highlighting SPEAR's pedagogical potential to enhance online engineering education through immersive AR experiences and social interaction. It offers a promising avenue for improving student engagement, comprehension, and performance. In addition, SPEAR facilitates future research into new learning theories and materials design strategies. Its versatility makes it a valuable tool for innovative online education approaches, potentially revolutionizing the learning experiences for students worldwide.
{"title":"Developing and Usability Testing of an Augmented Reality Tool for Online Engineering Education","authors":"Saurav Shrestha;Yongwei Shan;Robert Emerson;Zahrasadat Hosseini","doi":"10.1109/TLT.2024.3520413","DOIUrl":"https://doi.org/10.1109/TLT.2024.3520413","url":null,"abstract":"This article introduces the development process of social presence-enabled augmented reality (SPEAR) tool, an innovative augmented reality (AR) based learning application tailored for online engineering education. SPEAR focuses on a learning module of structural beam-bending, empowering users to seamlessly integrate 3-D virtual beams into their real-world environment, using the AR Foundation framework within the Unity game engine. Learners can explore structural mechanics by manipulating loads and positions. SPEAR leverages a custom C# script based on the finite element method to offer a real-time simulation of beam deformation, accompanied by visualizations of the moment/shear diagrams and bending stresses. In addition, the integration of a cloud-based voice chat feature, photon unity networking 2, enhances social presence, fostering collaborative learning. Usability testing conducted with extended reality developers and structural engineers, utilizing the system usability scale, confirmed SPEAR's user-friendliness and intuitive interface. Results indicate high levels of participant satisfaction, validating its design and functionality. This study contributes to the field by highlighting SPEAR's pedagogical potential to enhance online engineering education through immersive AR experiences and social interaction. It offers a promising avenue for improving student engagement, comprehension, and performance. In addition, SPEAR facilitates future research into new learning theories and materials design strategies. Its versatility makes it a valuable tool for innovative online education approaches, potentially revolutionizing the learning experiences for students worldwide.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"13-24"},"PeriodicalIF":2.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142937842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TLT.2024.3523199
Weijiao Huang;Khe Foon Hew
In an online learning environment, both instruction and assessments take place virtually where students are primarily responsible for managing their own learning. This requires a high level of self-regulation from students. Many online students, however, lack self-regulation skills and are ill-prepared for autonomous learning, which can cause students to feel disengaged from online activities. In addition, students tend to feel isolated during online activities due to limited social interaction. To address these challenges, this study explores the use of chatbots to facilitate students’ self-regulated learning strategies and promote social presence to alleviate their feelings of isolation. Using a two-phase mixed-methods design, this study evaluates students’ behavioral engagement, perceived self-regulated learning strategies, and social presence in chatbot-supported online learning. In the first phase (Stage I Study), 39 students engaged in a goal-setting chatbot activity that employed the SMART framework and social presence indicators. The findings served as the basis for improving the chatbot design in the second phase (Stage II Study), in which 25 students interacted with the revised chatbot, focusing on goal-setting, help-seeking, self-evaluation, and social interaction with instructor's presence. The results show that the students in both studies had positive online learning experiences with the chatbots. Follow-up interviews with students and instructors provide valuable insights and suggestions for refining the chatbot design, such as chatbots for ongoing monitoring of self-regulation habits and personalized social interaction. Drawing from the evidence, we discuss a set of chatbot design principles that support students’ self-regulated learning and social presence in online settings.
{"title":"Facilitating Online Self-Regulated Learning and Social Presence Using Chatbots: Evidence-Based Design Principles","authors":"Weijiao Huang;Khe Foon Hew","doi":"10.1109/TLT.2024.3523199","DOIUrl":"https://doi.org/10.1109/TLT.2024.3523199","url":null,"abstract":"In an online learning environment, both instruction and assessments take place virtually where students are primarily responsible for managing their own learning. This requires a high level of self-regulation from students. Many online students, however, lack self-regulation skills and are ill-prepared for autonomous learning, which can cause students to feel disengaged from online activities. In addition, students tend to feel isolated during online activities due to limited social interaction. To address these challenges, this study explores the use of chatbots to facilitate students’ self-regulated learning strategies and promote social presence to alleviate their feelings of isolation. Using a two-phase mixed-methods design, this study evaluates students’ behavioral engagement, perceived self-regulated learning strategies, and social presence in chatbot-supported online learning. In the first phase (Stage I Study), 39 students engaged in a goal-setting chatbot activity that employed the SMART framework and social presence indicators. The findings served as the basis for improving the chatbot design in the second phase (Stage II Study), in which 25 students interacted with the revised chatbot, focusing on goal-setting, help-seeking, self-evaluation, and social interaction with instructor's presence. The results show that the students in both studies had positive online learning experiences with the chatbots. Follow-up interviews with students and instructors provide valuable insights and suggestions for refining the chatbot design, such as chatbots for ongoing monitoring of self-regulation habits and personalized social interaction. Drawing from the evidence, we discuss a set of chatbot design principles that support students’ self-regulated learning and social presence in online settings.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"56-71"},"PeriodicalIF":2.9,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Knowledge tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive (AR) modeling on the sequence of former exercises has been proven effective for this task. One of the primary challenges in AR modeling for KT is effectively representing the anterior (preresponse) and posterior (postresponse) states of learners across exercises. Existing methods often employ complex model architectures to update learner states using question and response records. In this study, we propose a novel perspective on KT task by treating it as a generative process, consistent with the principles of AR models. We demonstrate that knowledge states can be directly represented through AR encodings on a question–response alternate sequence, where model generate the most probable representation in hidden state space by analyzing history interactions. This approach underpins our framework, termed alternate autoregressive KT (AAKT). In addition, we incorporate supplementary educational information, such as question-related skills, into our framework through an auxiliary task, and include extra exercise details, such as response time, as additional inputs. Our proposed framework is implemented using advanced AR technologies from Natural Language Generation for both training and prediction. Empirical evaluations on four real-world KT datasets indicate that AAKT consistently outperforms all baseline models in terms of area under the receiver operating characteristic curve, accuracy, and root mean square error. Furthermore, extensive ablation studies and visualized analysis validate the effectiveness of key components in AAKT.
{"title":"AAKT: Enhancing Knowledge Tracing With Alternate Autoregressive Modeling","authors":"Hao Zhou;Wenge Rong;Jianfei Zhang;Qing Sun;Yuanxin Ouyang;Zhang Xiong","doi":"10.1109/TLT.2024.3521898","DOIUrl":"https://doi.org/10.1109/TLT.2024.3521898","url":null,"abstract":"Knowledge tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive (AR) modeling on the sequence of former exercises has been proven effective for this task. One of the primary challenges in AR modeling for KT is effectively representing the anterior (preresponse) and posterior (postresponse) states of learners across exercises. Existing methods often employ complex model architectures to update learner states using question and response records. In this study, we propose a novel perspective on KT task by treating it as a generative process, consistent with the principles of AR models. We demonstrate that knowledge states can be directly represented through AR encodings on a question–response alternate sequence, where model generate the most probable representation in hidden state space by analyzing history interactions. This approach underpins our framework, termed alternate autoregressive KT (AAKT). In addition, we incorporate supplementary educational information, such as question-related skills, into our framework through an auxiliary task, and include extra exercise details, such as response time, as additional inputs. Our proposed framework is implemented using advanced AR technologies from Natural Language Generation for both training and prediction. Empirical evaluations on four real-world KT datasets indicate that AAKT consistently outperforms all baseline models in terms of area under the receiver operating characteristic curve, accuracy, and root mean square error. Furthermore, extensive ablation studies and visualized analysis validate the effectiveness of key components in AAKT.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"25-38"},"PeriodicalIF":2.9,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142937840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-19DOI: 10.1109/TLT.2024.3520329
Rafael Herrero-Álvarez;Rafael Arnay;Eduardo Segredo;Gara Miranda;Coromoto León
RoblockLLy is an educational robotics simulator designed for primary and secondary school students, whose goal is to increase their interest in science, technology, engineering, and mathematics. In the particular case of computer science, it allows developing computational thinking skills. It has been designed with ease of use in mind. This free tool is available through a web browser and does not need a complex installation or specific hardware requirements, allowing educational robotics to be introduced to a wide range of users by working on practical projects that will help them understand key concepts of robotics and programming. The effectiveness of RoblockLLy has been validated based on motivation, usability, and user experience criteria. The tool was validated with 212 secondary school students (12–16 years old). Specifically, motivation was measured with the Intrinsic Motivation Inventory, usability with the System Usability Scale, and user experience with the User Experience Questionnaire. Generally speaking, the results demonstrate that students perceived RoblockLLy as a novel and interesting tool. The ratings for usability were predominantly positive, although a few students indicated a preference for expert assistance. The overall rating of the user experience was positive as well, yet notable differences in attitudes toward motivation and usability were observed between genders.
{"title":"Using RoblockLLy in the Classroom: Bridging the Gap in Computer Science Education Through Robotics Simulation","authors":"Rafael Herrero-Álvarez;Rafael Arnay;Eduardo Segredo;Gara Miranda;Coromoto León","doi":"10.1109/TLT.2024.3520329","DOIUrl":"https://doi.org/10.1109/TLT.2024.3520329","url":null,"abstract":"RoblockLLy is an educational robotics simulator designed for primary and secondary school students, whose goal is to increase their interest in science, technology, engineering, and mathematics. In the particular case of computer science, it allows developing computational thinking skills. It has been designed with ease of use in mind. This free tool is available through a web browser and does not need a complex installation or specific hardware requirements, allowing educational robotics to be introduced to a wide range of users by working on practical projects that will help them understand key concepts of robotics and programming. The effectiveness of RoblockLLy has been validated based on motivation, usability, and user experience criteria. The tool was validated with 212 secondary school students (12–16 years old). Specifically, motivation was measured with the Intrinsic Motivation Inventory, usability with the System Usability Scale, and user experience with the User Experience Questionnaire. Generally speaking, the results demonstrate that students perceived RoblockLLy as a novel and interesting tool. The ratings for usability were predominantly positive, although a few students indicated a preference for expert assistance. The overall rating of the user experience was positive as well, yet notable differences in attitudes toward motivation and usability were observed between genders.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"39-52"},"PeriodicalIF":2.9,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10807249","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142937841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-17DOI: 10.1109/TLT.2024.3514832
Philemon Yalamu;Abdullah Al Mahmud;Caslon Chua
Cultural differences can impact how learning is delivered in higher education. Past studies have overlooked the impacts of specific cultures on learning and technology integration, and therefore, this article explores aspects of culture and resource implications for technology-enabled learning. The study collected data from students, lecturers, and university administrators at the University of Papua New Guinea via questionnaire (n = 58), focus group (n = 15), and interview (n = 2). Descriptive statistics of questionnaire responses supplemented by conventional content analysis of interview and focus group responses revealed perceptions of higher education and teaching in Papua New Guinea (PNG). Often, learning technologies are adopted without careful consideration of the users’ requirements, especially their cultural influences, which sometimes hinder the effective implementation of chosen technologies for learning. This article discusses the key findings related to technology limitations, cultural influences, communication issues, and other challenges unique to PNG. It highlights that students and lecturers are keen to embrace technology in teaching and learning; however, institutional constraints hinder the successful implementation of technology that would allow them to advance learning. This, coupled with cultural influences such as traditional customs, practices, and belief systems, also affects how Western education is delivered. The article concludes with recommendations for implementing culturally sensitive learning management systems that can accommodate infrastructure and social challenges.
{"title":"Investigating Culture and Resource-Sensitive Technology-Enabled Learning","authors":"Philemon Yalamu;Abdullah Al Mahmud;Caslon Chua","doi":"10.1109/TLT.2024.3514832","DOIUrl":"https://doi.org/10.1109/TLT.2024.3514832","url":null,"abstract":"Cultural differences can impact how learning is delivered in higher education. Past studies have overlooked the impacts of specific cultures on learning and technology integration, and therefore, this article explores aspects of culture and resource implications for technology-enabled learning. The study collected data from students, lecturers, and university administrators at the University of Papua New Guinea via questionnaire (<italic>n</i> = 58), focus group (<italic>n</i> = 15), and interview (<italic>n</i> = 2). Descriptive statistics of questionnaire responses supplemented by conventional content analysis of interview and focus group responses revealed perceptions of higher education and teaching in Papua New Guinea (PNG). Often, learning technologies are adopted without careful consideration of the users’ requirements, especially their cultural influences, which sometimes hinder the effective implementation of chosen technologies for learning. This article discusses the key findings related to technology limitations, cultural influences, communication issues, and other challenges unique to PNG. It highlights that students and lecturers are keen to embrace technology in teaching and learning; however, institutional constraints hinder the successful implementation of technology that would allow them to advance learning. This, coupled with cultural influences such as traditional customs, practices, and belief systems, also affects how Western education is delivered. The article concludes with recommendations for implementing culturally sensitive learning management systems that can accommodate infrastructure and social challenges.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"85-99"},"PeriodicalIF":2.9,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：