Pub Date : 2025-03-16DOI: 10.1109/TLT.2025.3570979
Sergio Tirado-Olivares;Rocío Mínguez-Pardo;Javier del Olmo-Muñoz;José A. González-Calero
Decimal misconceptions are a persistent challenge in mathematics education, often hindering students’ long-term understanding. This study examines how learning analytics (LA) can be effectively integrated into instructional sequences to address these misconceptions, providing teachers with real-time insights for formative assessment. Despite the growing presence of technology in education, LA remains underutilized at the primary level. The study involved 235 fifth- and sixth-grade students completing decimal number tasks through a Moodle-based platform. Students were assigned to one of three conditions: tasks based on correct examples (CE tasks, n = 79), erroneous examples (n = 80), or no tasks (control group, n = 76). Results indicate that example-based tasks significantly improve learning outcomes, particularly for students with lower prior knowledge, who benefited more from CE tasks. LA data effectively predicted student performance, demonstrating its potential as a formative assessment tool. Importantly, results suggest that the observed effects were consistent across male and female students. These findings highlight the need to integrate LA into daily teaching practice, enabling educators to identify misconceptions and tailor instruction accordingly. Given the positive student reception and the efficiency of LA-driven interventions, this study underscores its relevance for policy decisions aimed at enhancing mathematics education in primary schools.
{"title":"Utilizing Learning-Analytics-Based Activities as a Bridge to Enhance Elementary Students’ Mathematical Learning","authors":"Sergio Tirado-Olivares;Rocío Mínguez-Pardo;Javier del Olmo-Muñoz;José A. González-Calero","doi":"10.1109/TLT.2025.3570979","DOIUrl":"https://doi.org/10.1109/TLT.2025.3570979","url":null,"abstract":"Decimal misconceptions are a persistent challenge in mathematics education, often hindering students’ long-term understanding. This study examines how learning analytics (LA) can be effectively integrated into instructional sequences to address these misconceptions, providing teachers with real-time insights for formative assessment. Despite the growing presence of technology in education, LA remains underutilized at the primary level. The study involved 235 fifth- and sixth-grade students completing decimal number tasks through a Moodle-based platform. Students were assigned to one of three conditions: tasks based on correct examples (CE tasks, <italic>n</i> = 79), erroneous examples (<italic>n</i> = 80), or no tasks (control group, <italic>n</i> = 76). Results indicate that example-based tasks significantly improve learning outcomes, particularly for students with lower prior knowledge, who benefited more from CE tasks. LA data effectively predicted student performance, demonstrating its potential as a formative assessment tool. Importantly, results suggest that the observed effects were consistent across male and female students. These findings highlight the need to integrate LA into daily teaching practice, enabling educators to identify misconceptions and tailor instruction accordingly. Given the positive student reception and the efficiency of LA-driven interventions, this study underscores its relevance for policy decisions aimed at enhancing mathematics education in primary schools.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"593-605"},"PeriodicalIF":2.9,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11006300","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144232200","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 : 2025-03-14DOI: 10.1109/TLT.2025.3551256
Ka-Yan Fung;Kwong-Chiu Fung;Tze Leung Rick Lui;Kuen-Fung Sin;Lik-Hang Lee;Huamin Qu;Shenghui Song
Mastering the visually complex characters of the Chinese language poses significant challenges for students. The situation is even worse in Hong Kong, where students with different backgrounds, including students with/without dyslexia and non-Chinese speaking (NCS) students, are placed in the same class. Interactive design has been proven effective in enhancing students' learning performance and engagement. However, developing a learning tool for students with diverse backgrounds is challenging. This study proposes a robot-assisted Chinese learning system (RACLS) for those with diverse backgrounds and investigates its impact on learning motivation by a comparison study. In particular, 39 students participate in a five-day robot-led training program, while another 39 students received traditional teacher-led training. The comparison results show that RACLS can enhance the emotional engagement of students with dyslexia and strengthen the behavioral engagement of students without dyslexia. Interestingly, the learning motivation of NCS students in the experimental and control groups is enhanced similarly.
{"title":"Motivating Students With Different Needs to Learn Chinese in a Mixed-Background Classroom by Robot-Assisted Learning","authors":"Ka-Yan Fung;Kwong-Chiu Fung;Tze Leung Rick Lui;Kuen-Fung Sin;Lik-Hang Lee;Huamin Qu;Shenghui Song","doi":"10.1109/TLT.2025.3551256","DOIUrl":"https://doi.org/10.1109/TLT.2025.3551256","url":null,"abstract":"Mastering the visually complex characters of the Chinese language poses significant challenges for students. The situation is even worse in Hong Kong, where students with different backgrounds, including students with/without dyslexia and non-Chinese speaking (NCS) students, are placed in the same class. Interactive design has been proven effective in enhancing students' learning performance and engagement. However, developing a learning tool for students with diverse backgrounds is challenging. This study proposes a robot-assisted Chinese learning system (<italic>RACLS</i>) for those with diverse backgrounds and investigates its impact on learning motivation by a comparison study. In particular, 39 students participate in a five-day robot-led training program, while another 39 students received traditional teacher-led training. The comparison results show that <italic>RACLS</i> can enhance the emotional engagement of students with dyslexia and strengthen the behavioral engagement of students without dyslexia. Interestingly, the learning motivation of NCS students in the experimental and control groups is enhanced similarly.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"369-386"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10925892","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856347","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 : 2025-03-11DOI: 10.1109/TLT.2025.3550714
Yuanbin Diao;Yu-Sheng Su
With technological advancements, the Metaverse is being used to enhance learning effects and learning experience to ensure quality education. However, current empirical studies have produced varying results. Therefore, a meta-analysis was executed, leveraging the capabilities of Version 3 of the Comprehensive Meta-Analysis software to effectively synthesize the data, drawing insights from 34 studies published prior to October 2024. The goal was to analyze the effects of the Metaverse on quality education, and to investigate the moderating influences of four variables: Metaverse tools, educational stages, subject area, and treatment duration. The results showed that the overall effect sizes for learning effects and learning experience were 0.922 and 1.153, respectively, suggesting that the Metaverse substantially influences educational effects and learning experience. The four moderating variables all play a significant role in shaping the influence of the Metaverse on both learning effects and experience. This meta-analysis highlights a striking trend: the Metaverse's effects were especially pronounced for elementary and secondary school students, but less so for university students. In addition, the Metaverse's effects were most significant in science disciplines.
{"title":"Exploring the Impact of the Metaverse on Promoting Students’ Access to Quality Education: A Meta-Analysis","authors":"Yuanbin Diao;Yu-Sheng Su","doi":"10.1109/TLT.2025.3550714","DOIUrl":"https://doi.org/10.1109/TLT.2025.3550714","url":null,"abstract":"With technological advancements, the Metaverse is being used to enhance learning effects and learning experience to ensure quality education. However, current empirical studies have produced varying results. Therefore, a meta-analysis was executed, leveraging the capabilities of Version 3 of the Comprehensive Meta-Analysis software to effectively synthesize the data, drawing insights from 34 studies published prior to October 2024. The goal was to analyze the effects of the Metaverse on quality education, and to investigate the moderating influences of four variables: Metaverse tools, educational stages, subject area, and treatment duration. The results showed that the overall effect sizes for learning effects and learning experience were 0.922 and 1.153, respectively, suggesting that the Metaverse substantially influences educational effects and learning experience. The four moderating variables all play a significant role in shaping the influence of the Metaverse on both learning effects and experience. This meta-analysis highlights a striking trend: the Metaverse's effects were especially pronounced for elementary and secondary school students, but less so for university students. In addition, the Metaverse's effects were most significant in science disciplines.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"321-334"},"PeriodicalIF":2.9,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792886","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}
Despite the growing use of large language models (LLMs) in educational contexts, there is no evidence on how these can be operationalized by students to generate custom datasets suitable for teaching and learning. Moreover, in the context of network science, little is known about whether LLMs can replicate real-life network properties. This study addresses these gaps by evaluating the use of generative artificial intelligence (AI), specifically LLMs, to create synthetic network datasets for educational use. The analyzed data include students’ AI-generated network datasets, their interactions with the LLMs, and their perceptions and evaluations of the task's value. The results indicate that the LLM-generated networks had properties closer to real-life networks, such as higher transitivity, network density, and smaller mean distances compared to randomly generated networks. Thus, our findings show that students can use LLMs to produce synthetic networks with realistic structures while tailoring to the individual preferences of each student. The analysis of students’ interactions (prompts) with the LLMs revealed a predominant use of direct instructions and output specifications, with less emphasis on providing contextual details or iterative refinement of the LLM's responses, which highlights the need for AI literacy training to optimize students’ use of generative AI. Students’ perceptions of the use of AI were overall positive; they found using LLMs time saving and beneficial, although opinions on output relevance and quality varied, especially for assignments requiring replication of specific networks.
{"title":"Capturing the Process of Students' AI Interactions When Creating and Learning Complex Network Structures","authors":"Sonsoles López-Pernas;Kamila Misiejuk;Rogers Kaliisa;Mohammed Saqr","doi":"10.1109/TLT.2025.3568599","DOIUrl":"https://doi.org/10.1109/TLT.2025.3568599","url":null,"abstract":"Despite the growing use of large language models (LLMs) in educational contexts, there is no evidence on how these can be operationalized by students to generate custom datasets suitable for teaching and learning. Moreover, in the context of network science, little is known about whether LLMs can replicate real-life network properties. This study addresses these gaps by evaluating the use of generative artificial intelligence (AI), specifically LLMs, to create synthetic network datasets for educational use. The analyzed data include students’ AI-generated network datasets, their interactions with the LLMs, and their perceptions and evaluations of the task's value. The results indicate that the LLM-generated networks had properties closer to real-life networks, such as higher transitivity, network density, and smaller mean distances compared to randomly generated networks. Thus, our findings show that students can use LLMs to produce synthetic networks with realistic structures while tailoring to the individual preferences of each student. The analysis of students’ interactions (prompts) with the LLMs revealed a predominant use of direct instructions and output specifications, with less emphasis on providing contextual details or iterative refinement of the LLM's responses, which highlights the need for AI literacy training to optimize students’ use of generative AI. Students’ perceptions of the use of AI were overall positive; they found using LLMs time saving and beneficial, although opinions on output relevance and quality varied, especially for assignments requiring replication of specific networks.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"556-568"},"PeriodicalIF":2.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994563","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144170905","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 study investigates the cognitive and emotional processes involved in augmented reality (AR)-based learning. The study looks at learning outcomes, emotional responses, meditation, and attention using a comprehensive approach that includes self-assessment, electroencephalogram data gathering, and postexperiment questionnaires. In total, 12 participants, selected based on their English proficiency and lack of prior knowledge of the course material, engaged in AR-based learning, while a baseline reading condition was included to contextualize cognitive and emotional engagement. The study findings indicate that the AR group's participants demonstrated notably elevated attention and meditation levels, indicating heightened engagement and focus that is advantageous for efficient assimilation and retention of knowledge. Furthermore, AR learners reported feeling less tired and exhausted, which may have mitigated the negative emotional states that are frequently connected to learning activities. However, no significant differences in negative emotions were observed between the reading and AR groups. These results emphasize the value of customized AR environments for education goals and the need for more study to maximize learning outcomes and affective experiences in AR learning contexts.
{"title":"Exploring Augmented Reality's Influence on Cognitive Load and Emotional Dynamics Within AAV Training Environments","authors":"Fatema Rahimi;Abolghasem Sadeghi-Niaraki;Houbing Song;Huihui Wang;Soo-Mi Choi","doi":"10.1109/TLT.2025.3568416","DOIUrl":"https://doi.org/10.1109/TLT.2025.3568416","url":null,"abstract":"This study investigates the cognitive and emotional processes involved in augmented reality (AR)-based learning. The study looks at learning outcomes, emotional responses, meditation, and attention using a comprehensive approach that includes self-assessment, electroencephalogram data gathering, and postexperiment questionnaires. In total, 12 participants, selected based on their English proficiency and lack of prior knowledge of the course material, engaged in AR-based learning, while a baseline reading condition was included to contextualize cognitive and emotional engagement. The study findings indicate that the AR group's participants demonstrated notably elevated attention and meditation levels, indicating heightened engagement and focus that is advantageous for efficient assimilation and retention of knowledge. Furthermore, AR learners reported feeling less tired and exhausted, which may have mitigated the negative emotional states that are frequently connected to learning activities. However, no significant differences in negative emotions were observed between the reading and AR groups. These results emphasize the value of customized AR environments for education goals and the need for more study to maximize learning outcomes and affective experiences in AR learning contexts.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"581-592"},"PeriodicalIF":2.9,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144213627","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 : 2025-03-07DOI: 10.1109/TLT.2025.3567995
Deliang Wang;Yaqian Zheng;Jinjiang Li;Gaowei Chen
Researchers have increasingly utilized artificial intelligence to automatically analyze classroom dialogue, aiming to provide timely feedback to teachers due to its educational significance. However, traditional machine learning and deep learning models face challenges, such as limited performance and lack of generalizability, across various dimensions of classroom dialogue and educational contexts. Recent efforts to utilize large language models (LLMs) for classroom dialogue analysis have predominantly relied on prompt engineering techniques, primarily due to the high costs associated with full fine-tuning, which has resulted in suboptimal performance and areas needing improvement. We, therefore, propose the application of parameter-efficient fine-tuning (PEFT) techniques to enhance the performance of LLMs in classroom dialogue analysis. Specifically, we utilized low-rank adaptation, a prominent PEFT technique, to fine-tune three state-of-the-art LLMs—Llama-3.2-3B, Gemma-2-9B, and Mistral-7B-v0.3—targeting the analysis of both teachers' and students' dialogic moves within K-12 mathematics lessons. The experimental results indicate that, in comparison to fully fine-tuning BERT and RoBERTa models and prompting LLMs, LLMs fine-tuned using the PEFT technique achieve superior performance. Moreover, the PEFT approach significantly reduced the number of trainable parameters within the LLMs by over 300 times and decreased their training duration. Although the training time for PEFT-tuned LLMs was still longer than that required for fully fine-tuning BERT and RoBERTa, these LLMs demonstrated specialization in this specific dimension and generalizability to other tasks and contexts. We believe that the use of PEFT techniques presents a promising direction for future research in classroom dialogue analysis.
{"title":"Parameter-Efficiently Fine-Tuning Large Language Models for Classroom Dialogue Analysis","authors":"Deliang Wang;Yaqian Zheng;Jinjiang Li;Gaowei Chen","doi":"10.1109/TLT.2025.3567995","DOIUrl":"https://doi.org/10.1109/TLT.2025.3567995","url":null,"abstract":"Researchers have increasingly utilized artificial intelligence to automatically analyze classroom dialogue, aiming to provide timely feedback to teachers due to its educational significance. However, traditional machine learning and deep learning models face challenges, such as limited performance and lack of generalizability, across various dimensions of classroom dialogue and educational contexts. Recent efforts to utilize large language models (LLMs) for classroom dialogue analysis have predominantly relied on prompt engineering techniques, primarily due to the high costs associated with full fine-tuning, which has resulted in suboptimal performance and areas needing improvement. We, therefore, propose the application of parameter-efficient fine-tuning (PEFT) techniques to enhance the performance of LLMs in classroom dialogue analysis. Specifically, we utilized low-rank adaptation, a prominent PEFT technique, to fine-tune three state-of-the-art LLMs—Llama-3.2-3B, Gemma-2-9B, and Mistral-7B-v0.3—targeting the analysis of both teachers' and students' dialogic moves within K-12 mathematics lessons. The experimental results indicate that, in comparison to fully fine-tuning BERT and RoBERTa models and prompting LLMs, LLMs fine-tuned using the PEFT technique achieve superior performance. Moreover, the PEFT approach significantly reduced the number of trainable parameters within the LLMs by over 300 times and decreased their training duration. Although the training time for PEFT-tuned LLMs was still longer than that required for fully fine-tuning BERT and RoBERTa, these LLMs demonstrated specialization in this specific dimension and generalizability to other tasks and contexts. We believe that the use of PEFT techniques presents a promising direction for future research in classroom dialogue analysis.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"542-555"},"PeriodicalIF":2.9,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144125666","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 : 2025-03-05DOI: 10.1109/TLT.2025.3547321
Bei Cai;Ziyu He;Hong Fu;Yang Zheng;Yanjie Song
Much research has applied automated writing evaluation (AWE) systems to English writing instruction; however, understanding how students internalize and apply this feedback to reduce writing errors is difficult, largely due to the personal and private nature of this process. Therefore, this research utilized eye-tracking technology to explore the AWE system's effectiveness in reducing the writing errors of English major students. A total of 118 higher vocational college students majoring in English in China participated in this eight-week study. The experimental group studied with and received feedback from both the AWE system (Pigai) and the teacher, whereas the control group studied without the AWE system and only received teacher feedback. Eye-tracking experiments were conducted before and after the writing instruction. Participants’ responses during the eye-tracking experiment, first-person eye movement video data, and corresponding gaze data were collected. Leveraging the application of neural network technology in optical character recognition (OCR), combined with data from an eye-tracking device, we developed a system that can transform first-person eye movement video data and gaze data into heatmaps and eye-tracking indices conducive to analysis. Various data analysis methods were employed, including neural network algorithms, heatmap analysis, Mann–Whitney U test, independent-samples t-test, and Welch's t-test. The results for the post-eye-tracking experiment responses, heatmaps, and eye-tracking indices indicate the advantages of using the AWE system, which effectively enhances students’ ability to recognize writing errors while reducing processing time by facilitating the internalization of writing errors through continuous feedback on such errors, and enabling them to apply this knowledge to new materials, thereby recognizing writing errors more quickly and accurately, and thus helping them to reduce writing errors. The pedagogical implications are fully discussed.
{"title":"Reducing English Major Students’ Writing Errors With an Automated Writing Evaluation System: Evidence From Eye-Tracking Technology","authors":"Bei Cai;Ziyu He;Hong Fu;Yang Zheng;Yanjie Song","doi":"10.1109/TLT.2025.3547321","DOIUrl":"https://doi.org/10.1109/TLT.2025.3547321","url":null,"abstract":"Much research has applied automated writing evaluation (AWE) systems to English writing instruction; however, understanding how students internalize and apply this feedback to reduce writing errors is difficult, largely due to the personal and private nature of this process. Therefore, this research utilized eye-tracking technology to explore the AWE system's effectiveness in reducing the writing errors of English major students. A total of 118 higher vocational college students majoring in English in China participated in this eight-week study. The experimental group studied with and received feedback from both the AWE system (Pigai) and the teacher, whereas the control group studied without the AWE system and only received teacher feedback. Eye-tracking experiments were conducted before and after the writing instruction. Participants’ responses during the eye-tracking experiment, first-person eye movement video data, and corresponding gaze data were collected. Leveraging the application of neural network technology in optical character recognition (OCR), combined with data from an eye-tracking device, we developed a system that can transform first-person eye movement video data and gaze data into heatmaps and eye-tracking indices conducive to analysis. Various data analysis methods were employed, including neural network algorithms, heatmap analysis, Mann–Whitney U test, independent-samples <italic>t</i>-test, and Welch's <italic>t</i>-test. The results for the post-eye-tracking experiment responses, heatmaps, and eye-tracking indices indicate the advantages of using the AWE system, which effectively enhances students’ ability to recognize writing errors while reducing processing time by facilitating the internalization of writing errors through continuous feedback on such errors, and enabling them to apply this knowledge to new materials, thereby recognizing writing errors more quickly and accurately, and thus helping them to reduce writing errors. The pedagogical implications are fully discussed.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"304-320"},"PeriodicalIF":2.9,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909567","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761419","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 : 2025-02-28DOI: 10.1109/TLT.2025.3545084
Sirinda Palahan
The rise of online programming education has necessitated more effective personalized interactions, a gap that PythonPal aims to fill through its innovative learning system integrated with a chatbot. This research delves into PythonPal's potential to enhance the online learning experience, especially in contexts with high student-to-teacher ratios where there is a need for personalized feedback. PythonPal's design, featuring modules for conversation, tutorials, and exercises, was evaluated through student interactions and feedback. Key findings reveal PythonPal's proficiency in syntax error recognition and user query comprehension, with its intent classification model showing high accuracy. The system's performance in error feedback, though varied, demonstrates both strengths and areas for enhancement. Student feedback indicated satisfactory query understanding and feedback accuracy but also pointed out the need for faster responses and improved interaction quality. PythonPal's deployment promises to significantly enhance online programming education by providing immediate personalized feedback and interactive learning experiences, fostering a deeper understanding of programming concepts among students. These benefits mark a step forward in addressing the challenges of distance learning, making programming education more accessible and effective.
{"title":"PythonPal: Enhancing Online Programming Education Through Chatbot-Driven Personalized Feedback","authors":"Sirinda Palahan","doi":"10.1109/TLT.2025.3545084","DOIUrl":"https://doi.org/10.1109/TLT.2025.3545084","url":null,"abstract":"The rise of online programming education has necessitated more effective personalized interactions, a gap that PythonPal aims to fill through its innovative learning system integrated with a chatbot. This research delves into PythonPal's potential to enhance the online learning experience, especially in contexts with high student-to-teacher ratios where there is a need for personalized feedback. PythonPal's design, featuring modules for conversation, tutorials, and exercises, was evaluated through student interactions and feedback. Key findings reveal PythonPal's proficiency in syntax error recognition and user query comprehension, with its intent classification model showing high accuracy. The system's performance in error feedback, though varied, demonstrates both strengths and areas for enhancement. Student feedback indicated satisfactory query understanding and feedback accuracy but also pointed out the need for faster responses and improved interaction quality. PythonPal's deployment promises to significantly enhance online programming education by providing immediate personalized feedback and interactive learning experiences, fostering a deeper understanding of programming concepts among students. These benefits mark a step forward in addressing the challenges of distance learning, making programming education more accessible and effective.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"335-350"},"PeriodicalIF":2.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792885","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 : 2025-02-25DOI: 10.1109/TLT.2025.3545641
Nikola M. Luburić;Luka Ž. Dorić;Jelena J. Slivka;Dragan Lj. Vidaković;Katarina-Glorija G. Grujić;Aleksandar D. Kovačević;Simona B. Prokić
Software engineers are tasked with writing functionally correct code of high quality. Maintainability is a crucial code quality attribute that determines the ease of analyzing, modifying, reusing, and testing a software component. This quality attribute significantly affects the software's lifetime cost, contributing to developer productivity and other quality attributes. Consequently, academia and industry emphasize the need to train software engineers to build maintainable software code. Unfortunately, code maintainability is an ill-defined domain and is challenging to teach and learn. This problem is aggravated by a rising number of software engineering students and a lack of capable instructors. Existing instructors rely on scalable one-size-fits-all teaching methods that are ineffective. Advances in e-learning technologies can alleviate these issues. Our primary contribution is the design of a novel assessment item type, the maintainability challenge. It integrates into the standard intelligent tutoring system (ITS) architecture to develop skills for analyzing and refactoring high-level code maintainability issues. Our secondary contributions include the code maintainability knowledge component model and the implementation of an ITS that supports the maintainability challenge for the C# programming language. We designed, developed, and evaluated the ITS over two years of working with undergraduate students using a mixed-method approach anchored in design science. The empirical evaluations culminated with a field study with 59 undergraduate students. We report on the evaluation results that showcase the utility of our contributions. Our contributions support software engineering instructors in developing the code maintainability skills of their students at scale.
{"title":"An Intelligent Tutoring System to Support Code Maintainability Skill Development","authors":"Nikola M. Luburić;Luka Ž. Dorić;Jelena J. Slivka;Dragan Lj. Vidaković;Katarina-Glorija G. Grujić;Aleksandar D. Kovačević;Simona B. Prokić","doi":"10.1109/TLT.2025.3545641","DOIUrl":"https://doi.org/10.1109/TLT.2025.3545641","url":null,"abstract":"Software engineers are tasked with writing functionally correct code of high quality. Maintainability is a crucial code quality attribute that determines the ease of analyzing, modifying, reusing, and testing a software component. This quality attribute significantly affects the software's lifetime cost, contributing to developer productivity and other quality attributes. Consequently, academia and industry emphasize the need to train software engineers to build maintainable software code. Unfortunately, code maintainability is an ill-defined domain and is challenging to teach and learn. This problem is aggravated by a rising number of software engineering students and a lack of capable instructors. Existing instructors rely on scalable one-size-fits-all teaching methods that are ineffective. Advances in e-learning technologies can alleviate these issues. Our primary contribution is the design of a novel assessment item type, the maintainability challenge. It integrates into the standard intelligent tutoring system (ITS) architecture to develop skills for analyzing and refactoring high-level code maintainability issues. Our secondary contributions include the code maintainability knowledge component model and the implementation of an ITS that supports the maintainability challenge for the C# programming language. We designed, developed, and evaluated the ITS over two years of working with undergraduate students using a mixed-method approach anchored in design science. The empirical evaluations culminated with a field study with 59 undergraduate students. We report on the evaluation results that showcase the utility of our contributions. Our contributions support software engineering instructors in developing the code maintainability skills of their students at scale.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"289-303"},"PeriodicalIF":2.9,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706786","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 : 2025-02-24DOI: 10.1109/TLT.2025.3545436
Lorenzo Valente;Federico De Lorenzis;Davide Calandra;Fabrizio Lamberti
In recent years, first responders have faced increasing challenges in their operations, highlighting a growing need for specialized and comprehensive training. In particular, the firefighting incident commanders (ICs) are playing a pivotal role, providing directions to field operators and making critical decisions in emergency situations. Over time, traditional training tools in this field have evolved, reaching their pinnacle with augmented sand tables (ASTs). ASTs build on spatial augmented reality (SAR), a form of extended reality (XR) that utilizes projections. Although ASTs enable large-scale visualization of the morphological features of the terrain, by relying solely on SAR, it is not possible to fully leverage the potential of XR, which is increasingly recognized as a powerful tool for training. This work introduces a novel approach to training ICs by integrating ASTs with XR, incorporating a learning-by-doing methodology alongside an objective measurement of trainees' performance. To this end, an XR training system (XRTS) has been developed, combining the capabilities of an AST with personal mixed reality devices and integrating a physically accurate interactive fire simulator. This system was deployed within a forest firefighting IC training course. All the system components were designed based on the theoretical foundations of decision making to effectively develop the necessary skills. The proposed approach was compared with traditional AST-based training methods for these roles, focusing on the analysis of learning outcomes, user experience, usability, and cognitive load. The study demonstrated several advantages associated with the use of the XRTS, including improvements in training effectiveness and a notable reduction in overall cognitive load.
{"title":"Enhancing Sand-Table-Based Incident Command Training With Extended Reality and Interactive Simulations: A Use Case in Forest Firefighting","authors":"Lorenzo Valente;Federico De Lorenzis;Davide Calandra;Fabrizio Lamberti","doi":"10.1109/TLT.2025.3545436","DOIUrl":"https://doi.org/10.1109/TLT.2025.3545436","url":null,"abstract":"In recent years, first responders have faced increasing challenges in their operations, highlighting a growing need for specialized and comprehensive training. In particular, the firefighting incident commanders (ICs) are playing a pivotal role, providing directions to field operators and making critical decisions in emergency situations. Over time, traditional training tools in this field have evolved, reaching their pinnacle with augmented sand tables (ASTs). ASTs build on spatial augmented reality (SAR), a form of extended reality (XR) that utilizes projections. Although ASTs enable large-scale visualization of the morphological features of the terrain, by relying solely on SAR, it is not possible to fully leverage the potential of XR, which is increasingly recognized as a powerful tool for training. This work introduces a novel approach to training ICs by integrating ASTs with XR, incorporating a learning-by-doing methodology alongside an objective measurement of trainees' performance. To this end, an XR training system (XRTS) has been developed, combining the capabilities of an AST with personal mixed reality devices and integrating a physically accurate interactive fire simulator. This system was deployed within a forest firefighting IC training course. All the system components were designed based on the theoretical foundations of decision making to effectively develop the necessary skills. The proposed approach was compared with traditional AST-based training methods for these roles, focusing on the analysis of learning outcomes, user experience, usability, and cognitive load. The study demonstrated several advantages associated with the use of the XRTS, including improvements in training effectiveness and a notable reduction in overall cognitive load.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"18 ","pages":"273-288"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706765","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：