Pub Date : 2023-11-15DOI: 10.1186/s40561-023-00280-8
Kerimbayev Nurassyl, Zhanat Umirzakova, R. Shadiev, Vladimir Jotsov
{"title":"A student-centered approach using modern technologies in distance learning: a systematic review of the literature","authors":"Kerimbayev Nurassyl, Zhanat Umirzakova, R. Shadiev, Vladimir Jotsov","doi":"10.1186/s40561-023-00280-8","DOIUrl":"https://doi.org/10.1186/s40561-023-00280-8","url":null,"abstract":"","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"31 10","pages":"1-28"},"PeriodicalIF":4.8,"publicationDate":"2023-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139273024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1186/s40561-023-00279-1
Alwyn Vwen Yen Lee, Seng Chee Tan, Chew Lee Teo
Abstract Utilizing generative artificial intelligence, especially the more popularly used Generative Pre-trained Transformer (GPT) architecture, has made it possible to employ AI in ways that were previously not possible with conventional assessment and evaluation technologies for learning. As educational use cases and academic studies become increasingly prevalent, it is critical for education stakeholders to discuss design considerations and ideals that are key in supporting and augmenting learning via quality classroom discourse that sets the climate for student learning and thinking, and teachers’ transmission of expectations. In this paper, we seek to address how emergent technological advancements such as GPT, can be considered and utilized in designs that are consistent with the ideals of sustainable student discourse and knowledge creation. We showcase contemporary exemplars of possible designs and practices that are based on the pedagogy of knowledge building, with recent illustrations of how GPT may be utilized to sustain students’ knowledge building discourse. We also examine the potential effects and repercussions of technological utilization and misuse, along with insights into GPT’s role in supporting and enhancing knowledge building practices. We anticipate that the findings, through our exploration of designs and practices for knowledge creation, will be able to resonate with a broader audience and instigate meaningful change on issues of teaching and learning within smart learning environments.
{"title":"Designs and practices using generative AI for sustainable student discourse and knowledge creation","authors":"Alwyn Vwen Yen Lee, Seng Chee Tan, Chew Lee Teo","doi":"10.1186/s40561-023-00279-1","DOIUrl":"https://doi.org/10.1186/s40561-023-00279-1","url":null,"abstract":"Abstract Utilizing generative artificial intelligence, especially the more popularly used Generative Pre-trained Transformer (GPT) architecture, has made it possible to employ AI in ways that were previously not possible with conventional assessment and evaluation technologies for learning. As educational use cases and academic studies become increasingly prevalent, it is critical for education stakeholders to discuss design considerations and ideals that are key in supporting and augmenting learning via quality classroom discourse that sets the climate for student learning and thinking, and teachers’ transmission of expectations. In this paper, we seek to address how emergent technological advancements such as GPT, can be considered and utilized in designs that are consistent with the ideals of sustainable student discourse and knowledge creation. We showcase contemporary exemplars of possible designs and practices that are based on the pedagogy of knowledge building, with recent illustrations of how GPT may be utilized to sustain students’ knowledge building discourse. We also examine the potential effects and repercussions of technological utilization and misuse, along with insights into GPT’s role in supporting and enhancing knowledge building practices. We anticipate that the findings, through our exploration of designs and practices for knowledge creation, will be able to resonate with a broader audience and instigate meaningful change on issues of teaching and learning within smart learning environments.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"36 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135476625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.1186/s40561-023-00277-3
Brahim Hmedna, Aicha Bakki, Ali El Mezouary, Omar Baz
Abstract Massive Open Online Courses (MOOCs) are revolutionizing online education and have become a popular teaching platform. However, traditional MOOCs often overlook learners' individual needs and preferences when designing learning materials and activities, resulting in suboptimal learning experiences. To address this issue, this paper proposes an approach to identify learners' preferences for different learning styles by analyzing their traces in MOOC environments. The Felder–Silverman Learning Style Model is adopted as it is one of the most widely used models in technology-enhanced learning. This research focuses on developing a reliable predictive model that can accurately identify learning styles. Based on insights gained from our model implementation, we propose MOOCLS (MOOC Learning Styles), an intuitive visualization tool. MOOCLS can help teachers and instructional designers to gain significant insight into the diversity of learning styles within their MOOCs. This will allow them to design activities and content that better support the learning styles of their learners, which can lead to higher learning engagement, improved performance, and reduction in time to learn.
大规模在线开放课程(Massive Open Online Courses, MOOCs)正在掀起一场在线教育的革命，成为一种流行的教学平台。然而，传统的mooc在设计学习材料和活动时往往忽略了学习者的个性化需求和偏好，导致学习体验不理想。为了解决这一问题，本文提出了一种方法，通过分析学习者在MOOC环境中的痕迹来识别他们对不同学习风格的偏好。采用Felder-Silverman学习风格模型，因为它是技术增强学习中使用最广泛的模型之一。本研究的重点是开发一个可靠的预测模型，可以准确地识别学习风格。基于从我们的模型实现中获得的见解，我们提出了MOOCLS (MOOC学习风格)，一种直观的可视化工具。mooc可以帮助教师和教学设计师在mooc中获得对学习风格多样性的重要洞察。这将使他们能够设计更好地支持学习者学习风格的活动和内容，从而提高学习参与度，改善表现，减少学习时间。
{"title":"Unlocking teachers’ potential: MOOCLS, a visualization tool for enhancing MOOC teaching","authors":"Brahim Hmedna, Aicha Bakki, Ali El Mezouary, Omar Baz","doi":"10.1186/s40561-023-00277-3","DOIUrl":"https://doi.org/10.1186/s40561-023-00277-3","url":null,"abstract":"Abstract Massive Open Online Courses (MOOCs) are revolutionizing online education and have become a popular teaching platform. However, traditional MOOCs often overlook learners' individual needs and preferences when designing learning materials and activities, resulting in suboptimal learning experiences. To address this issue, this paper proposes an approach to identify learners' preferences for different learning styles by analyzing their traces in MOOC environments. The Felder–Silverman Learning Style Model is adopted as it is one of the most widely used models in technology-enhanced learning. This research focuses on developing a reliable predictive model that can accurately identify learning styles. Based on insights gained from our model implementation, we propose MOOCLS (MOOC Learning Styles), an intuitive visualization tool. MOOCLS can help teachers and instructional designers to gain significant insight into the diversity of learning styles within their MOOCs. This will allow them to design activities and content that better support the learning styles of their learners, which can lead to higher learning engagement, improved performance, and reduction in time to learn.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"12 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135633961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-06DOI: 10.1186/s40561-023-00276-4
Nikolaos Pellas
Abstract Artificial Intelligence (AI) and Machine Learning (ML) technologies offer the potential to support digital content creation and media production, providing opportunities for individuals from diverse sociodemographic backgrounds to engage in creative activities and enhance their multimedia video content. However, less attention has been paid to recent research exploring any possible relationships between AI-generated video creation and the sociodemographic variables of undergraduate students. This study aims to investigate the multifaceted relationship between AI-generated video content and sociodemographics by examining its implications for inclusivity, equity, and representation in the digital media landscape. An empirical study about the use of AI in video content creation was conducted with a diverse cohort of three hundred ninety-eighth undergraduate ( n = 398) students. Participants voluntarily took part and were tasked with conceiving and crafting their AI-generated video content. All instruments used were combined into a single web-based self-report questionnaire that was delivered to all participants via email. Key research findings demonstrate that students have a favorable disposition when it comes to incorporating AI-supported learning tasks. The factors fostering this favorable attitude among students include their age, the number of devices they use, the time they dedicate to utilizing technological resources, and their level of experience. Nevertheless, it is the student’s participation in AI training courses that exerts a direct impact on students’ ML attitudes, along with their level of contentment with the reliability of these technologies. This study contributes to a more comprehensive understanding of the transformative power of AI in video content creation and underscores the importance of considering instructional contexts and policies to ensure a fair and equitable digital media platform for students from diverse sociodemographic backgrounds.
{"title":"The influence of sociodemographic factors on students' attitudes toward AI-generated video content creation","authors":"Nikolaos Pellas","doi":"10.1186/s40561-023-00276-4","DOIUrl":"https://doi.org/10.1186/s40561-023-00276-4","url":null,"abstract":"Abstract Artificial Intelligence (AI) and Machine Learning (ML) technologies offer the potential to support digital content creation and media production, providing opportunities for individuals from diverse sociodemographic backgrounds to engage in creative activities and enhance their multimedia video content. However, less attention has been paid to recent research exploring any possible relationships between AI-generated video creation and the sociodemographic variables of undergraduate students. This study aims to investigate the multifaceted relationship between AI-generated video content and sociodemographics by examining its implications for inclusivity, equity, and representation in the digital media landscape. An empirical study about the use of AI in video content creation was conducted with a diverse cohort of three hundred ninety-eighth undergraduate ( n = 398) students. Participants voluntarily took part and were tasked with conceiving and crafting their AI-generated video content. All instruments used were combined into a single web-based self-report questionnaire that was delivered to all participants via email. Key research findings demonstrate that students have a favorable disposition when it comes to incorporating AI-supported learning tasks. The factors fostering this favorable attitude among students include their age, the number of devices they use, the time they dedicate to utilizing technological resources, and their level of experience. Nevertheless, it is the student’s participation in AI training courses that exerts a direct impact on students’ ML attitudes, along with their level of contentment with the reliability of these technologies. This study contributes to a more comprehensive understanding of the transformative power of AI in video content creation and underscores the importance of considering instructional contexts and policies to ensure a fair and equitable digital media platform for students from diverse sociodemographic backgrounds.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135634238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In Mainland China, the sports training process of most players is highly homogenized, the convergence of which makes them ineffectively be identified with their individual and specific profile and difficult for them to play the sports according to their strengths and characteristics. Moreover, existing sports training software does not differentiate between player types to provide customized persona. Therefore, efficient and personalized methods need to be provided to guide players towards more autonomous sports training. Current research shows that gamification design in the process of sports training can transform players' unique conscious behaviors into habits, thus increasing their autonomy. However, the current gamification design in sports training is only based on uniform gamification elements and does not take into account the player's motivation and gamification experience, which is one of the main reasons for the homogenization of sports training. Therefore, this study aimed to identify factors that contribute to the design of gamification systems in the field of sports training, as well as to determine the relationship between players' gamification experiences during sport. It will help the researchers to explore in depth the possibilities of learning environments for youth basketball training with the development of gamified experiences. This design-driven study performed both offline and online questionnaire research (N = 198), which was analyzed with the method of a 7-point Likert scale as well as the assistance of SPSS, identified potential for the establishment of a framework for analysing preferences for gamification design elements in the context of basketball training for young players. Based on the results, this paper finds that there is a correlation between immersion and achievement in gamification experiences and proposes a framework for gamification system design in the field of sports training and offers insight that may enable the development of gamification designs that can motivate players.
{"title":"Behavioural design of gamification elements and exploration of player types in youth basketball training","authors":"Zeping Feng, Newman Lau, Mengxiao Zhu, Mengru Liu, Rehe Refati, Xiao Huang, Kun-pyo Lee","doi":"10.1186/s40561-023-00278-2","DOIUrl":"https://doi.org/10.1186/s40561-023-00278-2","url":null,"abstract":"Abstract In Mainland China, the sports training process of most players is highly homogenized, the convergence of which makes them ineffectively be identified with their individual and specific profile and difficult for them to play the sports according to their strengths and characteristics. Moreover, existing sports training software does not differentiate between player types to provide customized persona. Therefore, efficient and personalized methods need to be provided to guide players towards more autonomous sports training. Current research shows that gamification design in the process of sports training can transform players' unique conscious behaviors into habits, thus increasing their autonomy. However, the current gamification design in sports training is only based on uniform gamification elements and does not take into account the player's motivation and gamification experience, which is one of the main reasons for the homogenization of sports training. Therefore, this study aimed to identify factors that contribute to the design of gamification systems in the field of sports training, as well as to determine the relationship between players' gamification experiences during sport. It will help the researchers to explore in depth the possibilities of learning environments for youth basketball training with the development of gamified experiences. This design-driven study performed both offline and online questionnaire research (N = 198), which was analyzed with the method of a 7-point Likert scale as well as the assistance of SPSS, identified potential for the establishment of a framework for analysing preferences for gamification design elements in the context of basketball training for young players. Based on the results, this paper finds that there is a correlation between immersion and achievement in gamification experiences and proposes a framework for gamification system design in the field of sports training and offers insight that may enable the development of gamification designs that can motivate players.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"189 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135321418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In recent years, initiatives and the resulting application of precision education have been applied with increasing frequency in Taiwan; the accompanying discourse has focused on identifying potential applications for artificial intelligence and how to use learning analytics to improve teaching quality and learning outcomes. This study used the established dropout risk prediction model to improve student learning effectiveness. The model was based on the academic portfolios of past students and built with statistical learning and deep learning methods. This study used this model to predict the dropout risk of 2205 freshmen enrolled in the fall semester of 2018 (graduated in June 2022) in the field of sustainable education. A total of 176 students with a dropout risk of more than 20% were considered high-risk students. After tracking and the appropriate guidance, the dropout risk of 91 students fell from > 20% to < 20%. To discuss the results from the perspective of gender and financial disadvantages, the improvement rate of the dropout risk for male students was 10.2% better than that of female students at 2.9%. The improvement rate in dropout risk for students with disadvantageous financial situations was as high as 12.0%, surpassing the 5.9% rate among general students. Overall, the dropout rate in the second year of the 2018 freshman cohort was lower than that of the 2016 and 2017 freshman cohorts. A predictive model established by statistical learning and deep learning methods was used as a tool to promote precision education, accurately and efficiently identifying students who are having difficulty learning, as well as leading to a better understanding of AI (artificial intelligence) in smart learning for sustainable education.
{"title":"Reducing dropout rate through a deep learning model for sustainable education: long-term tracking of learning outcomes of an undergraduate cohort from 2018 to 2021","authors":"Yi-Tzone Shiao, Cheng-Huan Chen, Ke-Fei Wu, Bae-Ling Chen, Yu-Hui Chou, Trong-Neng Wu","doi":"10.1186/s40561-023-00274-6","DOIUrl":"https://doi.org/10.1186/s40561-023-00274-6","url":null,"abstract":"Abstract In recent years, initiatives and the resulting application of precision education have been applied with increasing frequency in Taiwan; the accompanying discourse has focused on identifying potential applications for artificial intelligence and how to use learning analytics to improve teaching quality and learning outcomes. This study used the established dropout risk prediction model to improve student learning effectiveness. The model was based on the academic portfolios of past students and built with statistical learning and deep learning methods. This study used this model to predict the dropout risk of 2205 freshmen enrolled in the fall semester of 2018 (graduated in June 2022) in the field of sustainable education. A total of 176 students with a dropout risk of more than 20% were considered high-risk students. After tracking and the appropriate guidance, the dropout risk of 91 students fell from > 20% to < 20%. To discuss the results from the perspective of gender and financial disadvantages, the improvement rate of the dropout risk for male students was 10.2% better than that of female students at 2.9%. The improvement rate in dropout risk for students with disadvantageous financial situations was as high as 12.0%, surpassing the 5.9% rate among general students. Overall, the dropout rate in the second year of the 2018 freshman cohort was lower than that of the 2016 and 2017 freshman cohorts. A predictive model established by statistical learning and deep learning methods was used as a tool to promote precision education, accurately and efficiently identifying students who are having difficulty learning, as well as leading to a better understanding of AI (artificial intelligence) in smart learning for sustainable education.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"52 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134908294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-25DOI: 10.1186/s40561-023-00275-5
Yuet Kai Chan, Jae-Eun Oh, Henry Ma
Abstract This study explores the use of open educational resources (OERs) in studio-based learning and their influence on learning experiences. The research team conducted action research with 30 bachelor of arts students who were completing a video production subject. Students were required to learn from a website containing open online learning resources under a flipped classroom approach. A teaching schedule and website were designed according to several criteria. Research data were collected through observation, reflective journals, and interviews and were analyzed via thematic analysis. Participating students expressed their perceptions of benefits and hesitation in utilizing OERs in learning. They agreed that the use of OERs as flipped classroom learning materials could positively affect their learning, primarily through competence and learning autonomy as indicated in self-determination theory. This investigation provides teachers with valuable experience and suggestions for teaching and learning approaches that incorporate OERs into studio-based education. Students learn from OERs in which they can gain the most up-to-date technical knowledge in an autonomous environment. This experience indicates that this pedagogy greatly and positively influences students’ subject-learning experiences, learning outcomes, and self-learning skills.
{"title":"Using open educational resources in studio-based flipped classrooms: action research in video production learning","authors":"Yuet Kai Chan, Jae-Eun Oh, Henry Ma","doi":"10.1186/s40561-023-00275-5","DOIUrl":"https://doi.org/10.1186/s40561-023-00275-5","url":null,"abstract":"Abstract This study explores the use of open educational resources (OERs) in studio-based learning and their influence on learning experiences. The research team conducted action research with 30 bachelor of arts students who were completing a video production subject. Students were required to learn from a website containing open online learning resources under a flipped classroom approach. A teaching schedule and website were designed according to several criteria. Research data were collected through observation, reflective journals, and interviews and were analyzed via thematic analysis. Participating students expressed their perceptions of benefits and hesitation in utilizing OERs in learning. They agreed that the use of OERs as flipped classroom learning materials could positively affect their learning, primarily through competence and learning autonomy as indicated in self-determination theory. This investigation provides teachers with valuable experience and suggestions for teaching and learning approaches that incorporate OERs into studio-based education. Students learn from OERs in which they can gain the most up-to-date technical knowledge in an autonomous environment. This experience indicates that this pedagogy greatly and positively influences students’ subject-learning experiences, learning outcomes, and self-learning skills.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"21 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135113384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-24DOI: 10.1186/s40561-023-00272-8
Chinaza Solomon Ironsi
Abstract There is ongoing scientific discussion on the role of innovative technologies in enhancing teaching and learning. Technologies like augmented reality, virtual reality, mixed reality, artificial intelligence, and generative artificial intelligence have sparked debates in the broader literature. To contribute to ongoing discussions on these topics and to bridge gaps existing in works of literature on the potentials and challenges of innovative technologies like virtual reality, this paper provides insights from students and teachers on the use of virtual reality for teaching speaking skills so far lacking in academic prose in this domain. Given that this study only focused on obtaining student and teacher insights, a mixed-method research design that used questionnaires and interviews was implemented to investigate this study. After obtaining and analyzing data from 85 participants, the study found that although virtual reality could have improved students' speaking skills more efficiently, it was a fun and exciting learning experience for the students and teachers. Other novel findings of the study were instrumental in making pedagogic conclusions on the study's objective.
{"title":"Investigating the use of virtual reality to improve speaking skills: insights from students and teachers","authors":"Chinaza Solomon Ironsi","doi":"10.1186/s40561-023-00272-8","DOIUrl":"https://doi.org/10.1186/s40561-023-00272-8","url":null,"abstract":"Abstract There is ongoing scientific discussion on the role of innovative technologies in enhancing teaching and learning. Technologies like augmented reality, virtual reality, mixed reality, artificial intelligence, and generative artificial intelligence have sparked debates in the broader literature. To contribute to ongoing discussions on these topics and to bridge gaps existing in works of literature on the potentials and challenges of innovative technologies like virtual reality, this paper provides insights from students and teachers on the use of virtual reality for teaching speaking skills so far lacking in academic prose in this domain. Given that this study only focused on obtaining student and teacher insights, a mixed-method research design that used questionnaires and interviews was implemented to investigate this study. After obtaining and analyzing data from 85 participants, the study found that although virtual reality could have improved students' speaking skills more efficiently, it was a fun and exciting learning experience for the students and teachers. Other novel findings of the study were instrumental in making pedagogic conclusions on the study's objective.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135274205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-20DOI: 10.1186/s40561-023-00273-7
Yicong Liang, Di Zou, Haoran Xie, Fu Lee Wang
Abstract The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.
{"title":"Exploring the potential of using ChatGPT in physics education","authors":"Yicong Liang, Di Zou, Haoran Xie, Fu Lee Wang","doi":"10.1186/s40561-023-00273-7","DOIUrl":"https://doi.org/10.1186/s40561-023-00273-7","url":null,"abstract":"Abstract The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In recent years, smart learning environments have become central to modern education and support students and instructors through tools based on prediction and recommendation models. These methods often use learning material metadata, such as the knowledge contained in an exercise which is usually labeled by domain experts and is costly and difficult to scale. It recognizes that automated labeling eases the workload on experts, as seen in previous studies using automatic classification algorithms for research papers and Japanese mathematical exercises. However, these studies didn’t delve into fine-grained labeling. In addition to that, as the use of materials in the system becomes more widespread, paper materials are transformed into PDF formats, which can lead to incomplete extraction. However, there is less emphasis on labeling incomplete mathematical sentences to tackle this problem in the previous research. This study aims to achieve precise automated classification even from incomplete text inputs. To tackle these challenges, we propose a mathematical exercise labeling algorithm that can handle detailed labels, even for incomplete sentences, using word n-grams, compared to the state-of-the-art word embedding method. The results of the experiment show that mono-gram features with Random Forest models achieved the best performance with a macro F-measure of 92.50%, 61.28% for 24-class labeling and 297-class labeling tasks, respectively. The contribution of this research is showing that the proposed method based on traditional simple n-grams has the ability to find context-independent similarities in incomplete sentences and outperforms state-of-the-art word embedding methods in specific tasks like classifying short and incomplete texts.
{"title":"Automated labeling of PDF mathematical exercises with word N-grams VSM classification","authors":"Taisei Yamauchi, Brendan Flanagan, Ryosuke Nakamoto, Yiling Dai, Kyosuke Takami, Hiroaki Ogata","doi":"10.1186/s40561-023-00271-9","DOIUrl":"https://doi.org/10.1186/s40561-023-00271-9","url":null,"abstract":"Abstract In recent years, smart learning environments have become central to modern education and support students and instructors through tools based on prediction and recommendation models. These methods often use learning material metadata, such as the knowledge contained in an exercise which is usually labeled by domain experts and is costly and difficult to scale. It recognizes that automated labeling eases the workload on experts, as seen in previous studies using automatic classification algorithms for research papers and Japanese mathematical exercises. However, these studies didn’t delve into fine-grained labeling. In addition to that, as the use of materials in the system becomes more widespread, paper materials are transformed into PDF formats, which can lead to incomplete extraction. However, there is less emphasis on labeling incomplete mathematical sentences to tackle this problem in the previous research. This study aims to achieve precise automated classification even from incomplete text inputs. To tackle these challenges, we propose a mathematical exercise labeling algorithm that can handle detailed labels, even for incomplete sentences, using word n-grams, compared to the state-of-the-art word embedding method. The results of the experiment show that mono-gram features with Random Forest models achieved the best performance with a macro F-measure of 92.50%, 61.28% for 24-class labeling and 297-class labeling tasks, respectively. The contribution of this research is showing that the proposed method based on traditional simple n-grams has the ability to find context-independent similarities in incomplete sentences and outperforms state-of-the-art word embedding methods in specific tasks like classifying short and incomplete texts.","PeriodicalId":21774,"journal":{"name":"Smart Learning Environments","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135884740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：