Pub Date : 2024-06-05DOI: 10.1109/TLT.2024.3409702
Elizabeth B. Varghese;Marwa Qaraqe;Dena Al-Thani
In children with autism spectrum disorders (ASDs), assessing attention is crucial to understanding their behavioral and cognitive functioning. Attention difficulties are a common challenge for children with autism, significantly impacting their learning and social interactions. Traditional assessment methods often require skilled professionals to provide personalized interventions, which can be time consuming. In addition, existing approaches based on video and eye-tracking data have limitations in providing accurate educational interventions. This article proposes a noninvasive and objective method to assess and quantify attention levels in children with autism by utilizing head poses and gaze parameters. The proposed approach combines a deep learning model for extracting head pose parameters, algorithms to extract gaze parameters, machine learning models for the attention assessment task, and an ensemble of Bayesian neural networks for attention quantification. We conducted experiments involving 39 children (19 with ASD and 20 neurotypical children) by assigning various attention tasks and capturing their video and eye patterns using a webcam and an eye tracker. Results are analyzed for participant and task differences, which demonstrate that the proposed approach is successful in measuring a child's attention control and inattention. Ultimately, the developed attention assessment method using head poses and gaze parameters opens the door to developing real-time attention recognition systems that can enhance learning and provide targeted interventions.
{"title":"Attention Level Evaluation in Children With Autism: Leveraging Head Pose and Gaze Parameters From Videos for Educational Intervention","authors":"Elizabeth B. Varghese;Marwa Qaraqe;Dena Al-Thani","doi":"10.1109/TLT.2024.3409702","DOIUrl":"https://doi.org/10.1109/TLT.2024.3409702","url":null,"abstract":"In children with autism spectrum disorders (ASDs), assessing attention is crucial to understanding their behavioral and cognitive functioning. Attention difficulties are a common challenge for children with autism, significantly impacting their learning and social interactions. Traditional assessment methods often require skilled professionals to provide personalized interventions, which can be time consuming. In addition, existing approaches based on video and eye-tracking data have limitations in providing accurate educational interventions. This article proposes a noninvasive and objective method to assess and quantify attention levels in children with autism by utilizing head poses and gaze parameters. The proposed approach combines a deep learning model for extracting head pose parameters, algorithms to extract gaze parameters, machine learning models for the attention assessment task, and an ensemble of Bayesian neural networks for attention quantification. We conducted experiments involving 39 children (19 with ASD and 20 neurotypical children) by assigning various attention tasks and capturing their video and eye patterns using a webcam and an eye tracker. Results are analyzed for participant and task differences, which demonstrate that the proposed approach is successful in measuring a child's attention control and inattention. Ultimately, the developed attention assessment method using head poses and gaze parameters opens the door to developing real-time attention recognition systems that can enhance learning and provide targeted interventions.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1777-1793"},"PeriodicalIF":3.7,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141333988","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 : 2024-06-04DOI: 10.1109/TLT.2024.3409514
Maha Issa;Marwa Faraj;Niveen AbiGhannam
ChatGPT is a newly emerging artificial intelligence (AI) tool that can generate and assess written text. In this study, we aim to examine the extent to which it can correctly identify the structure of literature review sections in engineering research articles. For this purpose, we conducted a manual content analysis by classifying paragraphs of literature review sections into their corresponding categories that are based on Kwan's model, which is a labeling scheme for structuring literature reviews. We then asked ChatGPT to perform the same categorization and compared both outcomes. Numerical results do not imply a satisfactory performance of ChatGPT; therefore, writers cannot fully depend on it to edit their literature reviews. However, the AI chatbot displays an understanding of the given prompt and is able to respond beyond the classification task by giving supportive and useful explanations for the users. Such findings can be especially helpful for beginners who usually struggle to write comprehensive literature review sections since they highlight how users can benefit from this AI chatbot to revise their drafts at the level of content and organization. With further investigations and advancement, AI chatbots can also be used for teaching proper literature review writing and editing.
{"title":"Exploring ChatGPT's Ability to Classify the Structure of Literature Reviews in Engineering Research Articles","authors":"Maha Issa;Marwa Faraj;Niveen AbiGhannam","doi":"10.1109/TLT.2024.3409514","DOIUrl":"https://doi.org/10.1109/TLT.2024.3409514","url":null,"abstract":"ChatGPT is a newly emerging artificial intelligence (AI) tool that can generate and assess written text. In this study, we aim to examine the extent to which it can correctly identify the structure of literature review sections in engineering research articles. For this purpose, we conducted a manual content analysis by classifying paragraphs of literature review sections into their corresponding categories that are based on Kwan's model, which is a labeling scheme for structuring literature reviews. We then asked ChatGPT to perform the same categorization and compared both outcomes. Numerical results do not imply a satisfactory performance of ChatGPT; therefore, writers cannot fully depend on it to edit their literature reviews. However, the AI chatbot displays an understanding of the given prompt and is able to respond beyond the classification task by giving supportive and useful explanations for the users. Such findings can be especially helpful for beginners who usually struggle to write comprehensive literature review sections since they highlight how users can benefit from this AI chatbot to revise their drafts at the level of content and organization. With further investigations and advancement, AI chatbots can also be used for teaching proper literature review writing and editing.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1859-1868"},"PeriodicalIF":2.9,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141494861","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}
The impact of social media on teens’ mental health and development raises the need for educational interventions that equip them with the knowledge and skills to cope with dangerous situations. In spite of the growing effort to expand social media literacy among youngsters, social media interventions still rely on conventional methods that tend to prioritize cognitive skills while overlooking important socio-emotional competencies. To bridge this gap and offer innovative solutions to social media education, this article presents the narrative scripts (NS) approach implemented in a learning technology environment that integrates pedagogical strategies of authentic learning, narratives, and scripted collaborative learning within a simulated educational social media platform. A longitudinal study with 370 high school students in urban schools in Barcelona (Spain) was designed to assess NS in an intervention to foster the development of social media self-protection skills. The findings demonstrated that NS supported the development of social media self-protection skills, while the students expressed positive perceptions of their overall learning experience. The intervention notably enhanced the socio-emotional competencies of responsible decision-making, self-awareness, and social awareness. This research makes a valuable contribution to the design and development of technology aimed at facilitating authentic learning experiences for social media education, with a specific focus on interventions targeting socio-emotional competencies.
{"title":"Embedding Educational Narrative Scripts in a Social Media Environment","authors":"Emily Theophilou;René Lobo-Quintero;Davinia Hernández-Leo;Roberto Sánchez-Reina;Dimitri Ognibene","doi":"10.1109/TLT.2024.3409063","DOIUrl":"https://doi.org/10.1109/TLT.2024.3409063","url":null,"abstract":"The impact of social media on teens’ mental health and development raises the need for educational interventions that equip them with the knowledge and skills to cope with dangerous situations. In spite of the growing effort to expand social media literacy among youngsters, social media interventions still rely on conventional methods that tend to prioritize cognitive skills while overlooking important socio-emotional competencies. To bridge this gap and offer innovative solutions to social media education, this article presents the narrative scripts (NS) approach implemented in a learning technology environment that integrates pedagogical strategies of authentic learning, narratives, and scripted collaborative learning within a simulated educational social media platform. A longitudinal study with 370 high school students in urban schools in Barcelona (Spain) was designed to assess NS in an intervention to foster the development of social media self-protection skills. The findings demonstrated that NS supported the development of social media self-protection skills, while the students expressed positive perceptions of their overall learning experience. The intervention notably enhanced the socio-emotional competencies of responsible decision-making, self-awareness, and social awareness. This research makes a valuable contribution to the design and development of technology aimed at facilitating authentic learning experiences for social media education, with a specific focus on interventions targeting socio-emotional competencies.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1820-1833"},"PeriodicalIF":2.9,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10547444","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141494902","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 : 2024-04-30DOI: 10.1109/TLT.2024.3394807
Kangkang Li;Qian Yang;Xianmin Yang
The student-generated question (SGQ) strategy is an effective instructional strategy for developing students' higher order cognitive and critical thinking. However, assessing the quality of SGQs is time consuming and domain experts intensive. Previous automatic evaluation work focused on surface-level features of questions. To overcome this limitation, the state-of-the-art language models GPT-3.5 and GPT-4.0 were used to evaluate 1084 SGQs for topic relevance, clarity of expression, answerability, challenging, and cognitive level. Results showed that GPT-4.0 exhibits superior grading consistency with experts compared to GPT-3.5 in terms of topic relevance, clarity of expression, answerability, and difficulty level. GPT-3.5 and GPT-4.0 had low consistency with experts in terms of cognitive level. Over three rounds of testing, GPT-4.0 demonstrated higher stability in autograding when contrasted with GPT-3.5. In addition, to validate the effectiveness of GPT in evaluating SGQs from different domains and subjects, we have done the same experiment on a part of LearningQ dataset. We also discussed the attitudes of teachers and students toward automatic grading by GPT models. The findings underscore the potential of GPT-4.0 to assist teachers in evaluating the quality of SGQs. Nevertheless, the cognitive level assessment of SGQs still needs manual examination by teachers.
{"title":"Can Autograding of Student-Generated Questions Quality by ChatGPT Match Human Experts?","authors":"Kangkang Li;Qian Yang;Xianmin Yang","doi":"10.1109/TLT.2024.3394807","DOIUrl":"10.1109/TLT.2024.3394807","url":null,"abstract":"The student-generated question (SGQ) strategy is an effective instructional strategy for developing students' higher order cognitive and critical thinking. However, assessing the quality of SGQs is time consuming and domain experts intensive. Previous automatic evaluation work focused on surface-level features of questions. To overcome this limitation, the state-of-the-art language models GPT-3.5 and GPT-4.0 were used to evaluate 1084 SGQs for topic relevance, clarity of expression, answerability, challenging, and cognitive level. Results showed that GPT-4.0 exhibits superior grading consistency with experts compared to GPT-3.5 in terms of topic relevance, clarity of expression, answerability, and difficulty level. GPT-3.5 and GPT-4.0 had low consistency with experts in terms of cognitive level. Over three rounds of testing, GPT-4.0 demonstrated higher stability in autograding when contrasted with GPT-3.5. In addition, to validate the effectiveness of GPT in evaluating SGQs from different domains and subjects, we have done the same experiment on a part of LearningQ dataset. We also discussed the attitudes of teachers and students toward automatic grading by GPT models. The findings underscore the potential of GPT-4.0 to assist teachers in evaluating the quality of SGQs. Nevertheless, the cognitive level assessment of SGQs still needs manual examination by teachers.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1600-1610"},"PeriodicalIF":3.7,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140826861","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}
Data are fundamental to Learning Analytics (LA) research and practice. However, the ethical use of data, particularly in terms of respecting learners' privacy rights, is a potential barrier that could hinder the widespread adoption of LA in the education industry. Despite the policies and guidelines of privacy protection being available worldwide, this does not guarantee successful implementation in practice. It is necessary to develop practical approaches that would allow for the translation of the existing guidelines into practice. In this study, we examine an initial set of privacy-preserving mechanisms on a large-scale education dataset. The data utility is evaluated before and after privacy-preserving mechanisms are applied by fitting into commonly used LA models, providing an evaluation of the utility loss. We further explore the balance between preserving data privacy and maintaining data utility in LA. The results prove the compatibility between preserving learners' privacy and LA, providing a benchmark of utility loss to practitioners and researchers in the education sector. Our study reminds an imminent concern of data privacy and advocates that privacy preserving can and should be an integral part of the design of any LA technique.
数据是学习分析（LA）研究和实践的基础。然而，数据的道德使用，特别是在尊重学习者隐私权方面，是阻碍学习分析在教育行业广泛应用的潜在障碍。尽管全世界都有保护隐私的政策和指导方针，但这并不能保证在实践中成功实施。有必要制定切实可行的方法，以便将现有准则转化为实践。在本研究中，我们在大规模教育数据集上检验了一套初步的隐私保护机制。在应用隐私保护机制之前和之后，我们通过拟合常用的洛杉矶模型来评估数据效用，从而对效用损失进行评估。我们进一步探讨了在洛杉矶法中保护数据隐私和维护数据效用之间的平衡。研究结果证明了保护学习者隐私与 LA 之间的兼容性，为教育领域的从业人员和研究人员提供了效用损失基准。我们的研究提醒人们关注迫在眉睫的数据隐私问题，并倡导保护隐私可以而且应该成为任何学习方法技术设计中不可或缺的一部分。
{"title":"Preserving Both Privacy and Utility in Learning Analytics","authors":"Chen Zhan;Srećko Joksimović;Djazia Ladjal;Thierry Rakotoarivelo;Ruth Marshall;Abelardo Pardo","doi":"10.1109/TLT.2024.3393766","DOIUrl":"10.1109/TLT.2024.3393766","url":null,"abstract":"Data are fundamental to Learning Analytics (LA) research and practice. However, the ethical use of data, particularly in terms of respecting learners' privacy rights, is a potential barrier that could hinder the widespread adoption of LA in the education industry. Despite the policies and guidelines of privacy protection being available worldwide, this does not guarantee successful implementation in practice. It is necessary to develop practical approaches that would allow for the translation of the existing guidelines into practice. In this study, we examine an initial set of privacy-preserving mechanisms on a large-scale education dataset. The data utility is evaluated before and after privacy-preserving mechanisms are applied by fitting into commonly used LA models, providing an evaluation of the utility loss. We further explore the balance between preserving data privacy and maintaining data utility in LA. The results prove the compatibility between preserving learners' privacy and LA, providing a benchmark of utility loss to practitioners and researchers in the education sector. Our study reminds an imminent concern of data privacy and advocates that privacy preserving can and should be an integral part of the design of any LA technique.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1655-1667"},"PeriodicalIF":3.7,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140799519","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}
ChatGPT has received considerable attention in education, particularly in programming education because of its capabilities in automated code generation and program repairing and scoring. However, few empirical studies have investigated the use of ChatGPT to customize a learning system for scaffolding students’ computational thinking. Therefore, this article proposes an intelligent programming scaffolding system using ChatGPT following the theoretical framework of computational thinking and scaffolding. A mixed-method study was conducted to investigate the affordance of the scaffolding system using ChatGPT, and the findings show that most students had positive attitudes about the proposed system, and it was effective in improving their computational thinking generally but not their problem-solving skills. Therefore, more scaffolding strategies are discussed with the aim of improving student computational thinking, especially regarding problem-solving skills. The findings of this study are expected to guide future designs of generative artificial intelligence tools embedded in intelligent learning systems to foster students’ computational thinking and programming learning.
{"title":"Scaffolding Computational Thinking With ChatGPT","authors":"Jian Liao;Linrong Zhong;Longting Zhe;Handan Xu;Ming Liu;Tao Xie","doi":"10.1109/TLT.2024.3392896","DOIUrl":"10.1109/TLT.2024.3392896","url":null,"abstract":"ChatGPT has received considerable attention in education, particularly in programming education because of its capabilities in automated code generation and program repairing and scoring. However, few empirical studies have investigated the use of ChatGPT to customize a learning system for scaffolding students’ computational thinking. Therefore, this article proposes an intelligent programming scaffolding system using ChatGPT following the theoretical framework of computational thinking and scaffolding. A mixed-method study was conducted to investigate the affordance of the scaffolding system using ChatGPT, and the findings show that most students had positive attitudes about the proposed system, and it was effective in improving their computational thinking generally but not their problem-solving skills. Therefore, more scaffolding strategies are discussed with the aim of improving student computational thinking, especially regarding problem-solving skills. The findings of this study are expected to guide future designs of generative artificial intelligence tools embedded in intelligent learning systems to foster students’ computational thinking and programming learning.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1668-1682"},"PeriodicalIF":3.7,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10508087","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140799691","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 : 2024-04-23DOI: 10.1109/TLT.2024.3392830
Siu-Cheung Kong;Yin Yang
The advent of generative artificial intelligence (AI) has ignited an increase in discussions about generative AI tools in education. In this study, a human-centered learning and teaching framework that uses generative AI tools for self-regulated learning development through domain knowledge learning was proposed to catalyze changes in educational practices. The framework illustrates how generative AI tools can revolutionize educational practices and transform the processes of teaching and learning to become human-centered. It emphasizes the evolving roles of teachers, who increasingly become skillful facilitators and humanistic storytellers who craft differentiated instructions and attempt to develop students’ individualized learning. Drawing upon insights from neuroscience, the framework guides students to employ generative AI tools to augment their attentiveness, stimulate active engagement in learning, receive immediate feedback, and encourage self-reflection. The pedagogical approach is also reimagined; teachers equipped with generative AI tools and AI literacy can refine their teaching strategies to better equip students to meet future challenges. The practical application of the framework is demonstrated in a case study involving the development of Chinese language writing ability among primary students within a K–12 educational context. This article also reports the results of a 60-h development programme for teachers. Specifically, providing in-service teachers with cases involving uses of the proposed framework helped them to better understand the generative AI concepts and integrate them into their teaching and learning and increased their perceived ability to design AI-integrated courses that would enhance students’ attention, engagement, confidence, and satisfaction.
{"title":"A Human-Centered Learning and Teaching Framework Using Generative Artificial Intelligence for Self-Regulated Learning Development Through Domain Knowledge Learning in K–12 Settings","authors":"Siu-Cheung Kong;Yin Yang","doi":"10.1109/TLT.2024.3392830","DOIUrl":"10.1109/TLT.2024.3392830","url":null,"abstract":"The advent of generative artificial intelligence (AI) has ignited an increase in discussions about generative AI tools in education. In this study, a human-centered learning and teaching framework that uses generative AI tools for self-regulated learning development through domain knowledge learning was proposed to catalyze changes in educational practices. The framework illustrates how generative AI tools can revolutionize educational practices and transform the processes of teaching and learning to become human-centered. It emphasizes the evolving roles of teachers, who increasingly become skillful facilitators and humanistic storytellers who craft differentiated instructions and attempt to develop students’ individualized learning. Drawing upon insights from neuroscience, the framework guides students to employ generative AI tools to augment their attentiveness, stimulate active engagement in learning, receive immediate feedback, and encourage self-reflection. The pedagogical approach is also reimagined; teachers equipped with generative AI tools and AI literacy can refine their teaching strategies to better equip students to meet future challenges. The practical application of the framework is demonstrated in a case study involving the development of Chinese language writing ability among primary students within a K–12 educational context. This article also reports the results of a 60-h development programme for teachers. Specifically, providing in-service teachers with cases involving uses of the proposed framework helped them to better understand the generative AI concepts and integrate them into their teaching and learning and increased their perceived ability to design AI-integrated courses that would enhance students’ attention, engagement, confidence, and satisfaction.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1588-1599"},"PeriodicalIF":3.7,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140799518","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 : 2024-04-17DOI: 10.1109/TLT.2024.3390593
Xiang Wu;Huanhuan Wang;Yongting Zhang;Baowen Zou;Huaqing Hong
Generative artificial intelligence has become the focus of the intelligent education field, especially in the generation of personalized learning resources. Current learning resource generation methods recommend customized courses based on learning styles and interests, improving learning efficiency. However, these methods cannot generate personalized tutorials according to learners’ preferences, nor can they adjust tutorial content as moods or levels of knowledge change. Therefore, this study develops an intelligent tutorial-generating system (Self-GT) for self-aid learning, integrating cognitive computing and generative learning to capture learners’ dynamic preferences. The critical components of Self-GT are the tutorial-generating model based on cyclic deep reinforcement learning (RL) and the multimodal knowledge graph containing complex relationships. Specifically, the proposed RL model dynamically explores learners’ preferences from the temporal dimension, enabling RL agents to express learning behavior characteristics accurately and generate personalized tutorials. Then, relying on the internal self-developed education base and external Internet sources, a multimodal knowledge graph with multiple self-defined relationships is designed to enhance the precision of tutorial generation. Finally, the experimental results indicate that the Self-GT performs well in generating tutorials and has been successfully applied in the generating tutorial for “Hospital Network Architecture Planning and Design.”
{"title":"A Tutorial-Generating Method for Autonomous Online Learning","authors":"Xiang Wu;Huanhuan Wang;Yongting Zhang;Baowen Zou;Huaqing Hong","doi":"10.1109/TLT.2024.3390593","DOIUrl":"10.1109/TLT.2024.3390593","url":null,"abstract":"Generative artificial intelligence has become the focus of the intelligent education field, especially in the generation of personalized learning resources. Current learning resource generation methods recommend customized courses based on learning styles and interests, improving learning efficiency. However, these methods cannot generate personalized tutorials according to learners’ preferences, nor can they adjust tutorial content as moods or levels of knowledge change. Therefore, this study develops an intelligent tutorial-generating system (Self-GT) for self-aid learning, integrating cognitive computing and generative learning to capture learners’ dynamic preferences. The critical components of Self-GT are the tutorial-generating model based on cyclic deep reinforcement learning (RL) and the multimodal knowledge graph containing complex relationships. Specifically, the proposed RL model dynamically explores learners’ preferences from the temporal dimension, enabling RL agents to express learning behavior characteristics accurately and generate personalized tutorials. Then, relying on the internal self-developed education base and external Internet sources, a multimodal knowledge graph with multiple self-defined relationships is designed to enhance the precision of tutorial generation. Finally, the experimental results indicate that the Self-GT performs well in generating tutorials and has been successfully applied in the generating tutorial for “Hospital Network Architecture Planning and Design.”","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1558-1567"},"PeriodicalIF":3.7,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140614469","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 : 2024-04-10DOI: 10.1109/TLT.2024.3386098
Belle Li;Curtis J. Bonk;Chaoran Wang;Xiaojing Kou
This exploratory analysis investigates the integration of ChatGPT in self-directed learning (SDL). Specifically, this study examines YouTube content creators’ language-learning experiences and the role of ChatGPT in their SDL, building upon Song and Hill's conceptual model of SDL in online contexts. Thematic analysis of interviews with 19 YouTubers and relevant video contents reveals distinct constructs of ChatGPT-integrated SDL, suggesting a reconceptualization and refinement of the SDL framework in the consideration of generative artificial intelligence (AI). This framework emphasizes critical aspects of utilizing ChatGPT as an SDL tool on two distinct levels: 1) the interactive relationships and interplay between learners’ personal traits and their ongoing learning processes (local) and 2) the evolving nature of SDL in the rapidly advancing landscape of generative AI, with socio-political-cultural foundations of AI constantly shaping the learning environment where SDL occurs (global). The study highlights the potential of ChatGPT as a tool for promoting self-directed language learning (SDLL) and provides implications for the development of learning technologies and research on AI-facilitated SDL.
{"title":"Reconceptualizing Self-Directed Learning in the Era of Generative AI: An Exploratory Analysis of Language Learning","authors":"Belle Li;Curtis J. Bonk;Chaoran Wang;Xiaojing Kou","doi":"10.1109/TLT.2024.3386098","DOIUrl":"10.1109/TLT.2024.3386098","url":null,"abstract":"This exploratory analysis investigates the integration of ChatGPT in self-directed learning (SDL). Specifically, this study examines YouTube content creators’ language-learning experiences and the role of ChatGPT in their SDL, building upon Song and Hill's conceptual model of SDL in online contexts. Thematic analysis of interviews with 19 YouTubers and relevant video contents reveals distinct constructs of ChatGPT-integrated SDL, suggesting a reconceptualization and refinement of the SDL framework in the consideration of generative artificial intelligence (AI). This framework emphasizes critical aspects of utilizing ChatGPT as an SDL tool on two distinct levels: 1) the interactive relationships and interplay between learners’ personal traits and their ongoing learning processes (local) and 2) the evolving nature of SDL in the rapidly advancing landscape of generative AI, with socio-political-cultural foundations of AI constantly shaping the learning environment where SDL occurs (global). The study highlights the potential of ChatGPT as a tool for promoting self-directed language learning (SDLL) and provides implications for the development of learning technologies and research on AI-facilitated SDL.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1515-1529"},"PeriodicalIF":3.7,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140570306","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 : 2024-04-10DOI: 10.1109/TLT.2024.3387280
Ricardo Martin Fernandez;Felix Garcia-Loro;Gustavo R. Alves;Africa López-Rey;Russ Meier;Manuel Castro
For educational institutions in science, technology, engineering and mathematics (STEM) areas, the provision of practical learning scenarios is, traditionally, a major concern. In the 21st century, the explosion of information and communication technology (ICTs), as well as the universalization of low-cost hardware, has allowed the proliferation of technical solutions for any field, in the case of experimentation, encouraging the emergence and proliferation of nontraditional experimentation platforms. This movement has resulted in enriched practical environments, with wider adaptability for both students and teachers. In this article, the evolution of scholar production has been analyzed at the global level from 2000 to 2020. Current and emerging experimentation scenarios have been identified, specifying the scope and boundaries between them.
{"title":"New Scenarios and Trends in Nontraditional Laboratories From 2000 to 2020","authors":"Ricardo Martin Fernandez;Felix Garcia-Loro;Gustavo R. Alves;Africa López-Rey;Russ Meier;Manuel Castro","doi":"10.1109/TLT.2024.3387280","DOIUrl":"10.1109/TLT.2024.3387280","url":null,"abstract":"For educational institutions in science, technology, engineering and mathematics (STEM) areas, the provision of practical learning scenarios is, traditionally, a major concern. In the 21st century, the explosion of information and communication technology (ICTs), as well as the universalization of low-cost hardware, has allowed the proliferation of technical solutions for any field, in the case of experimentation, encouraging the emergence and proliferation of nontraditional experimentation platforms. This movement has resulted in enriched practical environments, with wider adaptability for both students and teachers. In this article, the evolution of scholar production has been analyzed at the global level from 2000 to 2020. Current and emerging experimentation scenarios have been identified, specifying the scope and boundaries between them.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"17 ","pages":"1568-1587"},"PeriodicalIF":3.7,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140570879","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：