Pub Date : 2024-04-01DOI: 10.1109/TLT.2024.3383773
Thi Thuy An Ngo;Thanh Tu Tran;Gia Khuong An;Phuong Thy Nguyen
The growing prevalence of advanced generative artificial intelligence chatbots, such as ChatGPT, in the educational sector has raised considerable interest in understanding their impact on student knowledge and exploring effective and sustainable implementation strategies. This research investigates the influence of knowledge management factors on the continuous usage of ChatGPT for educational purposes while concurrently evaluating student satisfaction with its use in learning. Using a quantitative approach, a structured questionnaire was administered to 513 Vietnamese university students via Google Forms for data collection. The partial least squares structural equation modeling statistical technique was employed to examine the relationships between identified factors and evaluate the research model. The results provided strong support for several hypotheses, revealing significant positive effects of expectation confirmation on perceived usefulness and satisfaction, as well as perceived usefulness on user satisfaction and continuous usage of ChatGPT. These findings suggest that when students recognize the usefulness of ChatGPT for their learnings, they experience higher satisfaction and are more likely to continue using it. In addition, knowledge acquisition significantly impacts both satisfaction and continuous usage of ChatGPT, while knowledge sharing and application influence satisfaction exclusively. This indicates that students prioritize knowledge acquisition over sharing and applying knowledge through ChatGPT. The study has theoretical and practical implications for ChatGPT developers, educators, and future research. Theoretically, it contributes to understanding satisfaction and continuous usage in educational settings, utilizing the expectation confirmation model and integrating knowledge management factors. Practically, it provides insights into comprehension and suggestions for enhancing user satisfaction and continuous usage of ChatGPT in education.
{"title":"ChatGPT for Educational Purposes: Investigating the Impact of Knowledge Management Factors on Student Satisfaction and Continuous Usage","authors":"Thi Thuy An Ngo;Thanh Tu Tran;Gia Khuong An;Phuong Thy Nguyen","doi":"10.1109/TLT.2024.3383773","DOIUrl":"https://doi.org/10.1109/TLT.2024.3383773","url":null,"abstract":"The growing prevalence of advanced generative artificial intelligence chatbots, such as ChatGPT, in the educational sector has raised considerable interest in understanding their impact on student knowledge and exploring effective and sustainable implementation strategies. This research investigates the influence of knowledge management factors on the continuous usage of ChatGPT for educational purposes while concurrently evaluating student satisfaction with its use in learning. Using a quantitative approach, a structured questionnaire was administered to 513 Vietnamese university students via Google Forms for data collection. The partial least squares structural equation modeling statistical technique was employed to examine the relationships between identified factors and evaluate the research model. The results provided strong support for several hypotheses, revealing significant positive effects of expectation confirmation on perceived usefulness and satisfaction, as well as perceived usefulness on user satisfaction and continuous usage of ChatGPT. These findings suggest that when students recognize the usefulness of ChatGPT for their learnings, they experience higher satisfaction and are more likely to continue using it. In addition, knowledge acquisition significantly impacts both satisfaction and continuous usage of ChatGPT, while knowledge sharing and application influence satisfaction exclusively. This indicates that students prioritize knowledge acquisition over sharing and applying knowledge through ChatGPT. The study has theoretical and practical implications for ChatGPT developers, educators, and future research. Theoretically, it contributes to understanding satisfaction and continuous usage in educational settings, utilizing the expectation confirmation model and integrating knowledge management factors. Practically, it provides insights into comprehension and suggestions for enhancing user satisfaction and continuous usage of ChatGPT in education.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1367-1378"},"PeriodicalIF":3.7,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140550172","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 : 2024-03-31DOI: 10.1109/TLT.2024.3406964
Seok-Hyun Ga;Changmi Park;Hyun-Jung Cha;Chan-Jong Kim
Data collection is crucial in securing evidence to support students’ arguments during scientific inquiries. However, due to the high costs associated with equipping schools with various measurement devices, students are limited in the scope of their scientific inquiry. Arduino can be proposed as a solution to the lack of measurement devices in schools. With Arduino, students can create various measurement devices by connecting different sensors, customize these devices to suit their inquiries, and implement remote sensing using the Internet of Things. However, even when promising new technology serves as a beneficial tool for teaching and learning, its successful integration into the educational system can be challenging if teachers struggle to use it. Technical issues often discourage teachers from incorporating potentially valuable technologies into their classrooms. This article examined the adoption of Arduino in three different cases involving teachers from various educational institutions: a gifted education center, an autonomous club activity in a middle school, and a local community center. We identified four major difficulties: 1) selection of appropriate technologies; 2) credibility issues with information from the Internet; 3) technical complexity due to the intervention of multiple variables; and 4) compliance issues with related acts and regulations. We described each of the technical challenges that teachers faced, in detail, and how they dealt with them. Finally, we discussed suggestions for reducing the barriers to Arduino use for teachers and proposed areas for further research.
{"title":"Science Teachers’ Technical Difficulties in Using Physical Computing and the Internet of Things Into School Science Inquiry","authors":"Seok-Hyun Ga;Changmi Park;Hyun-Jung Cha;Chan-Jong Kim","doi":"10.1109/TLT.2024.3406964","DOIUrl":"10.1109/TLT.2024.3406964","url":null,"abstract":"Data collection is crucial in securing evidence to support students’ arguments during scientific inquiries. However, due to the high costs associated with equipping schools with various measurement devices, students are limited in the scope of their scientific inquiry. Arduino can be proposed as a solution to the lack of measurement devices in schools. With Arduino, students can create various measurement devices by connecting different sensors, customize these devices to suit their inquiries, and implement remote sensing using the Internet of Things. However, even when promising new technology serves as a beneficial tool for teaching and learning, its successful integration into the educational system can be challenging if teachers struggle to use it. Technical issues often discourage teachers from incorporating potentially valuable technologies into their classrooms. This article examined the adoption of Arduino in three different cases involving teachers from various educational institutions: a gifted education center, an autonomous club activity in a middle school, and a local community center. We identified four major difficulties: 1) selection of appropriate technologies; 2) credibility issues with information from the Internet; 3) technical complexity due to the intervention of multiple variables; and 4) compliance issues with related acts and regulations. We described each of the technical challenges that teachers faced, in detail, and how they dealt with them. Finally, we discussed suggestions for reducing the barriers to Arduino use for teachers and proposed areas for further research.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1849-1858"},"PeriodicalIF":2.9,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191303","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 : 2024-03-28DOI: 10.1109/TLT.2024.3405966
Ye Zhang;Mo Wang;Jinlong He;Niantong Li;Yupeng Zhou;Haoxia Huang;Dunbo Cai;Minghao Yin
Diagnosing aesthetic perception plays a crucial role in deepening our understanding of student creativity, emotional expression, and the pursuit of lifelong learning within art education. This task encompasses the evaluation and analysis of students' sensitivity, preference, and capacity to perceive and appreciate beauty across different sensory domains. Currently, this assessment frequently relies on subjective evaluations of student artworks. There are two limitations: 1) the diagnosis is possibly limited by instructors' bias and 2) the heavy workload of instructors for conducting comprehensive assessments. These limitations motivate us to ask: Can we automatically and objectively conduct aesthetic perception diagnosis? To this end, we propose an innovative deep hybrid framework, AestheNet, to automatically evaluate aesthetic perception by analyzing numerous collected student paintings. More especially, we first utilize convolutional neural networks to extract the significant features from the student artworks. Then, we employ the transformer model to capture the intricate relationships among multiple aesthetic perception dimensions for objective diagnosis. Finally, we validate the effectiveness of the framework by creating a new dataset consisting of 2153 paintings drawn by 675 students. These paintings are annotated by human experts from 77 dimensions based on domain expertise. Extensive experiments have shown the effectiveness of AestheNet in aesthetic perception diagnosis. AestheNet is dedicated to overcoming the subjectivity inherent in traditional assessment methods, providing a new, quantifiable, and standardized way to evaluate aesthetic perception. This research not only opens up new perspectives in understanding students' aesthetic development during the art education process but also explores the innovation of using artificial intelligence technologies in the assessment of art education.
{"title":"AestheNet: Revolutionizing Aesthetic Perception Diagnosis in Education With Hybrid Deep Nets","authors":"Ye Zhang;Mo Wang;Jinlong He;Niantong Li;Yupeng Zhou;Haoxia Huang;Dunbo Cai;Minghao Yin","doi":"10.1109/TLT.2024.3405966","DOIUrl":"10.1109/TLT.2024.3405966","url":null,"abstract":"Diagnosing aesthetic perception plays a crucial role in deepening our understanding of student creativity, emotional expression, and the pursuit of lifelong learning within art education. This task encompasses the evaluation and analysis of students' sensitivity, preference, and capacity to perceive and appreciate beauty across different sensory domains. Currently, this assessment frequently relies on subjective evaluations of student artworks. There are two limitations: 1) the diagnosis is possibly limited by instructors' bias and 2) the heavy workload of instructors for conducting comprehensive assessments. These limitations motivate us to ask: \u0000<italic>Can we automatically and objectively conduct aesthetic perception diagnosis?</i>\u0000 To this end, we propose an innovative deep hybrid framework, AestheNet, to automatically evaluate aesthetic perception by analyzing numerous collected student paintings. More especially, we first utilize convolutional neural networks to extract the significant features from the student artworks. Then, we employ the transformer model to capture the intricate relationships among multiple aesthetic perception dimensions for objective diagnosis. Finally, we validate the effectiveness of the framework by creating a new dataset consisting of 2153 paintings drawn by 675 students. These paintings are annotated by human experts from 77 dimensions based on domain expertise. Extensive experiments have shown the effectiveness of AestheNet in aesthetic perception diagnosis. AestheNet is dedicated to overcoming the subjectivity inherent in traditional assessment methods, providing a new, quantifiable, and standardized way to evaluate aesthetic perception. This research not only opens up new perspectives in understanding students' aesthetic development during the art education process but also explores the innovation of using artificial intelligence technologies in the assessment of art education.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"2117-2129"},"PeriodicalIF":2.9,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191136","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 : 2024-03-28DOI: 10.1109/TLT.2024.3405565
Ricardo Conejo Muñoz;Beatriz Barros Blanco;José del Campo-Ávila;José L. Triviño Rodriguez
Automatic question generation and the assessment of procedural knowledge is still a challenging research topic. This article focuses on the case of it, the techniques of parsing grammars for compiler construction. There are two well-known techniques for parsing: top-down parsing with LL(1) and bottom-up with LR(1). Learning these techniques and learning to design grammars that can be parsed with these techniques requires practice. This article describes an application that covers all the tasks needed to automatize the learning and assessment process: 1) automatically generate context-free languages and grammars of different complexity; 2) pose different types of questions to the student with an appropriate response interface; 3) automatically correct the student answer, including grammar design for a given language; and 4) provide feedback on errors. The application has been implemented as a plug-in of the SIETTE assessment system that, in addition, can provide adaptive behavior for question selection. It has been successfully used by more than a thousand students for formative and summative assessment.
{"title":"Teaching Compilers: Automatic Question Generation and Intelligent Assessment of Grammars' Parsing","authors":"Ricardo Conejo Muñoz;Beatriz Barros Blanco;José del Campo-Ávila;José L. Triviño Rodriguez","doi":"10.1109/TLT.2024.3405565","DOIUrl":"10.1109/TLT.2024.3405565","url":null,"abstract":"Automatic question generation and the assessment of procedural knowledge is still a challenging research topic. This article focuses on the case of it, the techniques of parsing grammars for compiler construction. There are two well-known techniques for parsing: top-down parsing with LL(1) and bottom-up with LR(1). Learning these techniques and learning to design grammars that can be parsed with these techniques requires practice. This article describes an application that covers all the tasks needed to automatize the learning and assessment process: 1) automatically generate context-free languages and grammars of different complexity; 2) pose different types of questions to the student with an appropriate response interface; 3) automatically correct the student answer, including grammar design for a given language; and 4) provide feedback on errors. The application has been implemented as a plug-in of the SIETTE assessment system that, in addition, can provide adaptive behavior for question selection. It has been successfully used by more than a thousand students for formative and summative assessment.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1734-1744"},"PeriodicalIF":3.7,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10540326","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191137","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 : 2024-03-28DOI: 10.1109/TLT.2024.3406638
Ye Jia;Xiangzhi Eric Wang;Zackary P. T. Sin;Chen Li;Peter H. F. Ng;Xiao Huang;George Baciu;Jiannong Cao;Qing Li
One of the promises of edu-metaverse is its ability to provide a virtual environment that enables us to engage in learning activities that are similar to or on par with reality. The digital enhancements introduced in a virtual environment contribute to our increased expectations of novel learning experiences. However, despite its promising outcomes, there appears to be limited adoption of the edu-metaverse for practical learning at this time. We believe this can be attributed to the fact that there is a lack of investigation into learners' behavior given a social learning environment. This lack of investigation is critical, as without behavioral insight, it hinders the development of education material and the direction of an edu-metaverse. Upon completing our work with the pilot user studies, we provide the following insights: 1) compared to Zoom, a typical video conferencing and remote collaboration platform, learners in the edu-metaverse demonstrate heightened involvement in learning activities, particularly when drawing mind mapping aided by the embedded knowledge graph, and this copresence significantly boosts learner engagement and collaborative contribution to the learning tasks; and 2) the interaction and learning activity design within the edu-metaverse, especially concerning the use of MM.
教育虚拟世界（edu-metaverse）的承诺之一是，它能够提供一个虚拟环境，使我们能够参与与现实相似或相同的学习活动。虚拟环境中引入的数字增强功能有助于提高我们对新奇学习体验的期望。然而，尽管其成果令人期待，但目前在实际学习中采用教育虚拟世界的情况似乎很有限。我们认为，这是由于缺乏对学习者在社会学习环境中的行为的调查。这种调查的缺乏至关重要，因为没有对行为的深入了解，就会阻碍教育材料的开发和教育虚拟世界的发展方向。在完成试点用户研究工作后，我们提出了以下见解：1）与 Zoom（典型的视频会议和远程协作平台）相比，"edu-metaverse "中的学习者在学习活动中表现出更高的参与度，尤其是在绘制由嵌入式知识图谱辅助的思维导图时，这种共存性显著提高了学习者的参与度和对学习任务的协作贡献；以及2）"edu-metaverse "中的交互和学习活动设计，尤其是关于 MM.
{"title":"Knowledge-Graph-Driven Mind Mapping for Immersive Collaborative Learning: A Pilot Study in Edu-Metaverse","authors":"Ye Jia;Xiangzhi Eric Wang;Zackary P. T. Sin;Chen Li;Peter H. F. Ng;Xiao Huang;George Baciu;Jiannong Cao;Qing Li","doi":"10.1109/TLT.2024.3406638","DOIUrl":"10.1109/TLT.2024.3406638","url":null,"abstract":"One of the promises of edu-metaverse is its ability to provide a virtual environment that enables us to engage in learning activities that are similar to or on par with reality. The digital enhancements introduced in a virtual environment contribute to our increased expectations of novel learning experiences. However, despite its promising outcomes, there appears to be limited adoption of the edu-metaverse for practical learning at this time. We believe this can be attributed to the fact that there is a lack of investigation into learners' behavior given a social learning environment. This lack of investigation is critical, as without behavioral insight, it hinders the development of education material and the direction of an edu-metaverse. Upon completing our work with the pilot user studies, we provide the following insights: 1) compared to Zoom, a typical video conferencing and remote collaboration platform, learners in the edu-metaverse demonstrate heightened involvement in learning activities, particularly when drawing mind mapping aided by the embedded knowledge graph, and this copresence significantly boosts learner engagement and collaborative contribution to the learning tasks; and 2) the interaction and learning activity design within the edu-metaverse, especially concerning the use of MM.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1834-1848"},"PeriodicalIF":2.9,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10540301","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191508","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}
Teaching robotics with the robot operating system (ROS) is valuable for instating good programming practices but requires significant setup steps from the learner. Providing a ready-made ROS learning environment over the web can make robotics more accessible; however, most of the previous remote labs have abstracted the authentic ROS developer environment either for didactical or technological reasons, or do not give the possibility to program physical robots. In this article, we present a remote web lab that employs virtual network computing and Docker to serve in-browser desktop workstations, where learning tasks can be completed on both the physical and simulated robots. The learners can reserve access to the remote lab through a learning management interface, which also includes tools for administering the remote lab. The system allows anyone to experiment with ROS without configuring any software locally and was successfully trialed in an online ROS course.
{"title":"Open Remote Web Lab for Learning Robotics and ROS With Physical and Simulated Robots in an Authentic Developer Environment","authors":"Dāvis Krūmiņš;Sandra Schumann;Veiko Vunder;Rauno Põlluäär;Kristjan Laht;Renno Raudmäe;Alvo Aabloo;Karl Kruusamäe","doi":"10.1109/TLT.2024.3381858","DOIUrl":"10.1109/TLT.2024.3381858","url":null,"abstract":"Teaching robotics with the robot operating system (ROS) is valuable for instating good programming practices but requires significant setup steps from the learner. Providing a ready-made ROS learning environment over the web can make robotics more accessible; however, most of the previous remote labs have abstracted the authentic ROS developer environment either for didactical or technological reasons, or do not give the possibility to program physical robots. In this article, we present a remote web lab that employs virtual network computing and Docker to serve in-browser desktop workstations, where learning tasks can be completed on both the physical and simulated robots. The learners can reserve access to the remote lab through a learning management interface, which also includes tools for administering the remote lab. The system allows anyone to experiment with ROS without configuring any software locally and was successfully trialed in an online ROS course.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1325-1338"},"PeriodicalIF":3.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10480223","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140316076","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 : 2024-03-27DOI: 10.1109/TLT.2024.3382000
Huaiya Liu;Yuyue Zhang;Jiyou Jia
Intelligent tutoring systems (ITSs) aim to deliver personalized learning support to each learner, aligning with the educational aspiration of many countries, including China. ITSs' personalized support is mainly achieved by providing individual prompts to learners when they encounter difficulties in problem-solving. The guiding principles and methods of prompts have been less investigated in previous ITS literatures. Based on relevant learning theories, such as self-regulated learning theory, zone of proximal development, scaffolding and heuristic teaching, we proposed seven guiding principles for designing ITS prompts and designed the guiding and adaptive prompts for the difficult questions in a mathematical ITS, math intelligent assessment and teaching system V2.0. In order to verify the effectiveness of this ITS with the aforementioned prompts, we conducted a 2 × 2 quasi-experiment in a high school, where the experimental group followed a process of “pretest, practice with general prompts and adaptive tutoring, and posttest,” while the control group followed a process of “pretest, practice with only general prompts, and posttest.” We collected the pre and posttest scores of both the experimental and control groups, and log data from the student model within the ITS for the experimental group students. The data analysis indicated that although the experimental group scored lower than the control group in the pretest, they scored higher in the posttest and spent less completion time. The drilled problems and the prompts provided to the experimental group students were personalized. In conclusion, the design principles for guiding and adaptive prompts in the ITS can provide personalized guidance and support for students, thus effectively improve their performance. Those principles are not only valuable for the subject mathematics but also can contribute significantly to the prompt design of other subjects, thereby bolstering the global pursuit of personalized education.
智能辅导系统（ITS）旨在为每个学习者提供个性化的学习支持，符合包括中国在内的许多国家的教育愿望。智能辅导系统的个性化支持主要是通过在学习者遇到解决问题的困难时提供个别提示来实现的。关于提示的指导原则和方法，以往的 ITS 文献研究较少。基于相关学习理论，如自我调节学习理论、近端发展区、支架式教学和启发式教学等，我们提出了设计ITS提示的七项指导原则，并在数学ITS--数学智能测评与教学系统V2.0中设计了疑难问题的指导性和自适应提示。为了验证该 ITS 使用上述提示语的效果，我们在一所高中进行了 2 × 2 准实验，实验组按照 "前测、使用一般提示语练习和自适应辅导、后测 "的流程进行，而对照组则按照 "前测、仅使用一般提示语练习、后测 "的流程进行。我们收集了实验组和对照组的前测和后测成绩，以及实验组学生在 ITS 中的学生模型日志数据。数据分析显示，虽然实验组在前测中的得分低于对照组，但他们在后测中的得分却高于对照组，而且花费的完成时间更少。为实验组学生提供的演练问题和提示都是个性化的。总之，智能学习系统中的指导和自适应提示设计原则可以为学生提供个性化的指导和支持，从而有效提高他们的成绩。这些原则不仅对数学学科有价值，对其他学科的提示设计也大有裨益，从而推动全球对个性化教育的追求。
{"title":"The Design of Guiding and Adaptive Prompts for Intelligent Tutoring Systems and Its Effect on Students’ Mathematics Learning","authors":"Huaiya Liu;Yuyue Zhang;Jiyou Jia","doi":"10.1109/TLT.2024.3382000","DOIUrl":"10.1109/TLT.2024.3382000","url":null,"abstract":"Intelligent tutoring systems (ITSs) aim to deliver personalized learning support to each learner, aligning with the educational aspiration of many countries, including China. ITSs' personalized support is mainly achieved by providing individual prompts to learners when they encounter difficulties in problem-solving. The guiding principles and methods of prompts have been less investigated in previous ITS literatures. Based on relevant learning theories, such as self-regulated learning theory, zone of proximal development, scaffolding and heuristic teaching, we proposed seven guiding principles for designing ITS prompts and designed the guiding and adaptive prompts for the difficult questions in a mathematical ITS, math intelligent assessment and teaching system V2.0. In order to verify the effectiveness of this ITS with the aforementioned prompts, we conducted a 2 × 2 quasi-experiment in a high school, where the experimental group followed a process of “pretest, practice with general prompts and adaptive tutoring, and posttest,” while the control group followed a process of “pretest, practice with only general prompts, and posttest.” We collected the pre and posttest scores of both the experimental and control groups, and log data from the student model within the ITS for the experimental group students. The data analysis indicated that although the experimental group scored lower than the control group in the pretest, they scored higher in the posttest and spent less completion time. The drilled problems and the prompts provided to the experimental group students were personalized. In conclusion, the design principles for guiding and adaptive prompts in the ITS can provide personalized guidance and support for students, thus effectively improve their performance. Those principles are not only valuable for the subject mathematics but also can contribute significantly to the prompt design of other subjects, thereby bolstering the global pursuit of personalized education.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1379-1389"},"PeriodicalIF":3.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140316237","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}
Reading comprehension is a widely adopted method for learning English, involving reading articles and answering related questions. However, the reading comprehension training typically focuses on the skill level required for a standardized learning stage, without considering the impact of individual differences in linguistic competence. This article presents a personalized support system for reading comprehension, named chat generative pretrained transformer (ChatGPT)-based personalized reading comprehension support (ChatPRCS), based on the zone of proximal development (ZPD) theory. It leverages the advanced capabilities of large language models, exemplified by ChatGPT. ChatPRCS employs methods, including skill prediction, question generation and automatic evaluation, to enhance reading comprehension instruction. First, a ZPD-based algorithm is developed to predict students' reading comprehension skills. This algorithm analyzes historical data to generate questions with appropriate difficulty. Second, a series of ChatGPT prompt patterns is proposed to address two key aspects of reading comprehension objectives: question generation, and automated evaluation. These patterns further improve the quality of generated questions. Finally, by integrating personalized skill prediction and reading comprehension prompt patterns, ChatPRCS is validated through a series of experiments. Empirical results demonstrate that it provides learners with high-quality reading comprehension questions that are broadly aligned with expert-crafted questions at a statistical level. Furthermore, this study investigates the effect of the system on learning achievement, learning motivation, and cognitive load, providing further evidence of its effectiveness in instructing English reading comprehension.
{"title":"ChatPRCS: A Personalized Support System for English Reading Comprehension Based on ChatGPT","authors":"Xizhe Wang;Yihua Zhong;Changqin Huang;Xiaodi Huang","doi":"10.1109/TLT.2024.3405747","DOIUrl":"10.1109/TLT.2024.3405747","url":null,"abstract":"Reading comprehension is a widely adopted method for learning English, involving reading articles and answering related questions. However, the reading comprehension training typically focuses on the skill level required for a standardized learning stage, without considering the impact of individual differences in linguistic competence. This article presents a personalized support system for reading comprehension, named chat generative pretrained transformer (ChatGPT)-based personalized reading comprehension support (ChatPRCS), based on the zone of proximal development (ZPD) theory. It leverages the advanced capabilities of large language models, exemplified by ChatGPT. ChatPRCS employs methods, including skill prediction, question generation and automatic evaluation, to enhance reading comprehension instruction. First, a ZPD-based algorithm is developed to predict students' reading comprehension skills. This algorithm analyzes historical data to generate questions with appropriate difficulty. Second, a series of ChatGPT prompt patterns is proposed to address two key aspects of reading comprehension objectives: question generation, and automated evaluation. These patterns further improve the quality of generated questions. Finally, by integrating personalized skill prediction and reading comprehension prompt patterns, ChatPRCS is validated through a series of experiments. Empirical results demonstrate that it provides learners with high-quality reading comprehension questions that are broadly aligned with expert-crafted questions at a statistical level. Furthermore, this study investigates the effect of the system on learning achievement, learning motivation, and cognitive load, providing further evidence of its effectiveness in instructing English reading comprehension.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1762-1776"},"PeriodicalIF":3.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141171260","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 : 2024-03-27DOI: 10.1109/TLT.2024.3382217
Hua Ma;Wen Zhao;Yuqi Tang;Peiji Huang;Haibin Zhu;Wensheng Tang;Keqin Li
To prevent students from learning risks and improve teachers' teaching quality, it is of great significance to provide accurate early warning of learning performance to students by analyzing their interactions through an e-learning system. In existing research, the correlations between learning risks and students' changing cognitive abilities or learning states are still underexplored, and the personalized early warning is unavailable for students at different levels. To accurately identify the possible learning risks faced by students at different levels, this article proposes a personalized early warning approach to learning performance for college students via cognitive ability and learning state modeling. In this approach, students' learning process data and historical performance data are analyzed to track students' cognitive abilities in the whole learning process, and model their learning states from four dimensions, i.e., learning quality, learning engagement, latent learning state, and historical learning state. Then, the Adaboost algorithm is used to predict students' learning performance, and an evaluation rule with five levels is designed to dynamically provide multilevel personalized early warning to students. Finally, the comparative experiments based on real-world datasets demonstrate that the proposed approach could effectively predict all students' learning performance, and provide accurate early warning services to them.
{"title":"Personalized Early Warning of Learning Performance for College Students: A Multilevel Approach via Cognitive Ability and Learning State Modeling","authors":"Hua Ma;Wen Zhao;Yuqi Tang;Peiji Huang;Haibin Zhu;Wensheng Tang;Keqin Li","doi":"10.1109/TLT.2024.3382217","DOIUrl":"10.1109/TLT.2024.3382217","url":null,"abstract":"To prevent students from learning risks and improve teachers' teaching quality, it is of great significance to provide accurate early warning of learning performance to students by analyzing their interactions through an e-learning system. In existing research, the correlations between learning risks and students' changing cognitive abilities or learning states are still underexplored, and the personalized early warning is unavailable for students at different levels. To accurately identify the possible learning risks faced by students at different levels, this article proposes a personalized early warning approach to learning performance for college students via cognitive ability and learning state modeling. In this approach, students' learning process data and historical performance data are analyzed to track students' cognitive abilities in the whole learning process, and model their learning states from four dimensions, i.e., learning quality, learning engagement, latent learning state, and historical learning state. Then, the Adaboost algorithm is used to predict students' learning performance, and an evaluation rule with five levels is designed to dynamically provide multilevel personalized early warning to students. Finally, the comparative experiments based on real-world datasets demonstrate that the proposed approach could effectively predict all students' learning performance, and provide accurate early warning services to them.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1440-1453"},"PeriodicalIF":3.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140316238","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) is an intelligent educational technology used to model students' learning progress and mastery in adaptive learning environments for personalized education. Despite utilizing deep learning models in KT, current approaches often oversimplify students' exercise records into knowledge sequences, which fail to explore the rich information within individual questions. In addition, existing KT models tend to neglect the complex, higher order relationships between questions and latent concepts. Therefore, we introduce a novel model called feature crosses information-based KT (FCIKT) to explore the intricate interplay between questions, latent concepts, and question difficulties. FCIKT utilizes a fusion module to perform feature crosses operations on questions, integrating information from our constructed multirelational heterogeneous graph using graph convolutional networks. We deployed a multihead attention mechanism, which enriches the static embedding representations of questions and concepts with dynamic semantic information to simulate real-world scenarios of problem-solving. We also used gated recurrent units to dynamically capture and update the students' knowledge state for final prediction. Extensive experiments demonstrated the validity and interpretability of our proposed model.
{"title":"Modeling Student Performance Using Feature Crosses Information for Knowledge Tracing","authors":"Lixiang Xu;Zhanlong Wang;Suojuan Zhang;Xin Yuan;Minjuan Wang;Enhong Chen","doi":"10.1109/TLT.2024.3381045","DOIUrl":"10.1109/TLT.2024.3381045","url":null,"abstract":"Knowledge tracing (KT) is an intelligent educational technology used to model students' learning progress and mastery in adaptive learning environments for personalized education. Despite utilizing deep learning models in KT, current approaches often oversimplify students' exercise records into knowledge sequences, which fail to explore the rich information within individual questions. In addition, existing KT models tend to neglect the complex, higher order relationships between questions and latent concepts. Therefore, we introduce a novel model called feature crosses information-based KT (FCIKT) to explore the intricate interplay between questions, latent concepts, and question difficulties. FCIKT utilizes a fusion module to perform feature crosses operations on questions, integrating information from our constructed multirelational heterogeneous graph using graph convolutional networks. We deployed a multihead attention mechanism, which enriches the static embedding representations of questions and concepts with dynamic semantic information to simulate real-world scenarios of problem-solving. We also used gated recurrent units to dynamically capture and update the students' knowledge state for final prediction. Extensive experiments demonstrated the validity and interpretability of our proposed model.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1390-1403"},"PeriodicalIF":2.9,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140198823","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：