Computers & Education最新文献

Enhancing teacher collaboration for technology integration: the impact of transformational leadership

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-21 DOI: 10.1016/j.compedu.2025.105331

Maria-Luisa Schmitz , Chiara Antonietti , Tessa Consoli , Philipp Gonon , Alberto Cattaneo , Dominik Petko

The study explored how school principals' transformational leadership impacts formal and informal teacher collaboration for technology integration. Goal clarity and the strategic importance of technology integration in Swiss upper-secondary schools were considered as mediators. Analyzing data from a survey of 2247 teachers using multilevel correlation and structural equation modeling (SEM) with cluster-robust standard errors, we found that principals’ transformational leadership is significantly and positively correlated with both formal and informal teacher collaboration, goal clarity, and strategic importance of technology integration. Further, SEM analysis revealed that transformational leadership has a significant, positive, and direct effect on formal collaboration but has only a significant indirect effect on informal collaboration. Moreover, the strategic importance of technology integration mediates the relationship between transformational leadership and formal collaboration as well as informal collaboration. However, goal clarity was only a significant mediator for the relationship between transformational leadership and informal collaboration. These findings suggest that for effective technology integration, school principals should prioritize transformational leadership to ensure a high strategic importance and goal clarity regarding technology integration which in turn have a positive impact on formal and informal collaboration.

{"title":"Enhancing teacher collaboration for technology integration: the impact of transformational leadership","authors":"Maria-Luisa Schmitz , Chiara Antonietti , Tessa Consoli , Philipp Gonon , Alberto Cattaneo , Dominik Petko","doi":"10.1016/j.compedu.2025.105331","DOIUrl":"10.1016/j.compedu.2025.105331","url":null,"abstract":"<div><div>The study explored how school principals' transformational leadership impacts formal and informal teacher collaboration for technology integration. Goal clarity and the strategic importance of technology integration in Swiss upper-secondary schools were considered as mediators. Analyzing data from a survey of 2247 teachers using multilevel correlation and structural equation modeling (SEM) with cluster-robust standard errors, we found that principals’ transformational leadership is significantly and positively correlated with both formal and informal teacher collaboration, goal clarity, and strategic importance of technology integration. Further, SEM analysis revealed that transformational leadership has a significant, positive, and direct effect on formal collaboration but has only a significant indirect effect on informal collaboration. Moreover, the strategic importance of technology integration mediates the relationship between transformational leadership and formal collaboration as well as informal collaboration. However, goal clarity was only a significant mediator for the relationship between transformational leadership and informal collaboration. These findings suggest that for effective technology integration, school principals should prioritize transformational leadership to ensure a high strategic importance and goal clarity regarding technology integration which in turn have a positive impact on formal and informal collaboration.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"234 ","pages":"Article 105331"},"PeriodicalIF":8.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Should educators be concerned? The impact of short videos on rational thinking and learning: A comparative analysis

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-21 DOI: 10.1016/j.compedu.2025.105330

Thorsten Otto

Short videos are highly attractive and are becoming increasingly popular among young adults due to their unique properties. However, they also pose a risk of getting used to surface processing and suppressing slow analytic thinking. So far, little is known about the potential impact of short video use (SVU) on learning variables. Therefore, this series of studies aimed to examine the consequences of SVU on rational thinking, academic delay of gratification (ADOG), and a surface learning approach (Study 1) and examine the situational impact of watching a short video collection on those variables except ADOG (Study 2). Further, it was examined whether short video-based learning material is suitable for teaching low-complex material (Study 2). In Study 1, participants (n = 169) completed questionnaires regarding SVU, rational thinking, ADOG, and surface learning approach. For Study 2, participants (n = 123) took part in an online experiment with a 2 (short video collection; present vs. not present) x 2 (learning material; short video-based vs. text-based) between-subject design, completed questionnaires regarding SVU, rational thinking, surface learning approach and answered a quiz regarding knowledge acquisition. The findings reveal that SVU is negatively associated with rational thinking and positively associated with a surface learning approach. Watching a short video collection led to a higher situational surface learning approach, and participants who learned with short videos scored lower on the quiz than those who learned with text. Limitations, implications, and future directions are discussed.

{"title":"Should educators be concerned? The impact of short videos on rational thinking and learning: A comparative analysis","authors":"Thorsten Otto","doi":"10.1016/j.compedu.2025.105330","DOIUrl":"10.1016/j.compedu.2025.105330","url":null,"abstract":"<div><div>Short videos are highly attractive and are becoming increasingly popular among young adults due to their unique properties. However, they also pose a risk of getting used to surface processing and suppressing slow analytic thinking. So far, little is known about the potential impact of short video use (SVU) on learning variables. Therefore, this series of studies aimed to examine the consequences of SVU on rational thinking, academic delay of gratification (ADOG), and a surface learning approach (Study 1) and examine the situational impact of watching a short video collection on those variables except ADOG (Study 2). Further, it was examined whether short video-based learning material is suitable for teaching low-complex material (Study 2). In Study 1, participants (<em>n</em> = 169) completed questionnaires regarding SVU, rational thinking, ADOG, and surface learning approach. For Study 2, participants (<em>n</em> = 123) took part in an online experiment with a 2 (short video collection; present vs. not present) x 2 (learning material; short video-based vs. text-based) between-subject design, completed questionnaires regarding SVU, rational thinking, surface learning approach and answered a quiz regarding knowledge acquisition. The findings reveal that SVU is negatively associated with rational thinking and positively associated with a surface learning approach. Watching a short video collection led to a higher situational surface learning approach, and participants who learned with short videos scored lower on the quiz than those who learned with text. Limitations, implications, and future directions are discussed.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"234 ","pages":"Article 105330"},"PeriodicalIF":8.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Measuring undergraduate students' reliance on Generative AI during problem-solving: Scale development and validation

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-19 DOI: 10.1016/j.compedu.2025.105329

Chenyu Hou , Gaoxia Zhu , Vidya Sudarshan , Fun Siong Lim , Yew Soon Ong

Reliance on AI describes the behavioral patterns of when and how individuals depend on AI suggestions, and appropriate reliance patterns are necessary to achieve effective human-AI collaboration. Traditional measures often link reliance to decision-making outcomes, which may not be suitable for complex problem-solving tasks where outcomes are not binary (i.e., correct or incorrect) or immediately clear. Therefore, this study aims to develop a scale to measure undergraduate students' behaviors of using Generative AI during problem-solving tasks without directly linking them to specific outcomes. We conducted an exploratory factor analysis on 800 responses collected after students finished one problem-solving activity, which revealed four distinct factors: reflective use, cautious use, thoughtless use, and collaborative use. The overall scale has reached sufficient internal reliability (Cronbach's alpha = .84). Two confirmatory factor analyses (CFAs) were conducted to validate the factors using the remaining 730 responses from this activity and 1173 responses from another problem-solving activity. CFA indices showed adequate model fit for data from both problem-solving tasks, suggesting that the scale can be applied to various human-AI problem-solving tasks. This study offers a validated scale to measure students' reliance behaviors in different human-AI problem-solving activities and provides implications for educators to responsively integrate Generative AI in higher education.

{"title":"Measuring undergraduate students' reliance on Generative AI during problem-solving: Scale development and validation","authors":"Chenyu Hou , Gaoxia Zhu , Vidya Sudarshan , Fun Siong Lim , Yew Soon Ong","doi":"10.1016/j.compedu.2025.105329","DOIUrl":"10.1016/j.compedu.2025.105329","url":null,"abstract":"<div><div>Reliance on AI describes the behavioral patterns of when and how individuals depend on AI suggestions, and appropriate reliance patterns are necessary to achieve effective human-AI collaboration. Traditional measures often link reliance to decision-making outcomes, which may not be suitable for complex problem-solving tasks where outcomes are not binary (i.e., correct or incorrect) or immediately clear. Therefore, this study aims to develop a scale to measure undergraduate students' behaviors of using Generative AI during problem-solving tasks without directly linking them to specific outcomes. We conducted an exploratory factor analysis on 800 responses collected after students finished one problem-solving activity, which revealed four distinct factors: reflective use, cautious use, thoughtless use, and collaborative use. The overall scale has reached sufficient internal reliability (Cronbach's alpha = .84). Two confirmatory factor analyses (CFAs) were conducted to validate the factors using the remaining 730 responses from this activity and 1173 responses from another problem-solving activity. CFA indices showed adequate model fit for data from both problem-solving tasks, suggesting that the scale can be applied to various human-AI problem-solving tasks. This study offers a validated scale to measure students' reliance behaviors in different human-AI problem-solving activities and provides implications for educators to responsively integrate Generative AI in higher education.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"234 ","pages":"Article 105329"},"PeriodicalIF":8.9,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sustaining focus when It's hardest: Emotional design strengthens sustained learning, especially in contexts with attractive alternatives

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-12 DOI: 10.1016/j.compedu.2025.105313

Tino Endres , Charlotte Vössing , K. Ann Renninger , Alexander Eitel , Alexander Renkl

Learners increasingly use digital devices such as laptops or tablets for studying. While these devices offer advantages, they also pose challenges. They present attractive alternative opportunities for learners, such as communication or entertainment opportunities that may distract from learning. Such alternatives increase demand for self-control, particularly over time. We investigated the potential of emotional design in learning materials to support self-control by triggering and maintaining situational interest, thereby reducing the mental load required for self-control. We hypothesize that emotional design becomes especially effective in distraction-prone learning situations, such as during extended learning durations or when attractive alternative opportunities are present. We employed a 2 × 2 × 2 mixed design, varying video design (neutral vs. emotional) and opportunity presentation (no opportunity vs. opportunity presented) as between-subjects factors, and learning phase (beginning vs. end of the video) as a within-subjects factor. Our participants (N = 144) learned from a 16-min video on photography. We assessed triggered and maintained situational interest, mental load, and learning outcomes. Emotional design interacted with the learning phase, enhancing learning outcomes particularly at the end of the video. This learning benefit was mediated by the development of situational interest and a reduction in mental load. The positive impact of emotional design on learning at the end of the video was significantly stronger when an alternative opportunity was present (three-way interaction). Emotional design seems to be particularly helpful when self-control demands are high. Such conditions include extended learning sessions, the presence of attractive alternatives, or situations where multiple self-control demands come together.

{"title":"Sustaining focus when It's hardest: Emotional design strengthens sustained learning, especially in contexts with attractive alternatives","authors":"Tino Endres , Charlotte Vössing , K. Ann Renninger , Alexander Eitel , Alexander Renkl","doi":"10.1016/j.compedu.2025.105313","DOIUrl":"10.1016/j.compedu.2025.105313","url":null,"abstract":"<div><div>Learners increasingly use digital devices such as laptops or tablets for studying. While these devices offer advantages, they also pose challenges. They present attractive alternative opportunities for learners, such as communication or entertainment opportunities that may distract from learning. Such alternatives increase demand for self-control, particularly over time. We investigated the potential of emotional design in learning materials to support self-control by triggering and maintaining situational interest, thereby reducing the mental load required for self-control. We hypothesize that emotional design becomes especially effective in distraction-prone learning situations, such as during extended learning durations or when attractive alternative opportunities are present. We employed a 2 × 2 × 2 mixed design, varying video design (neutral vs. emotional) and opportunity presentation (no opportunity vs. opportunity presented) as between-subjects factors, and learning phase (beginning vs. end of the video) as a within-subjects factor. Our participants (<em>N</em> = 144) learned from a 16-min video on photography. We assessed triggered and maintained situational interest, mental load, and learning outcomes. Emotional design interacted with the learning phase, enhancing learning outcomes particularly at the end of the video. This learning benefit was mediated by the development of situational interest and a reduction in mental load. The positive impact of emotional design on learning at the end of the video was significantly stronger when an alternative opportunity was present (three-way interaction). Emotional design seems to be particularly helpful when self-control demands are high. Such conditions include extended learning sessions, the presence of attractive alternatives, or situations where multiple self-control demands come together.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"233 ","pages":"Article 105313"},"PeriodicalIF":8.9,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Increasing knowledge about plasma and plasma donation through a serious game: Evidence from a mixed-method study

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-11 DOI: 10.1016/j.compedu.2025.105325

Alexandra Ciausescu , Eva-Maria Merz , Rene Bekkers , Arjen de Wit

Many European countries are facing plasma shortages, with lack of awareness and knowledge about plasma donation being a potential explanation for low donor numbers. One approach to increasing knowledge and awareness about plasma is through informal educational methods, such as serious games. We developed a serious game focused on plasma and plasma donation for children and adolescents (8–17 years) in the Netherlands and tested it with 636 participants in collaboration with the science museum NEMO Amsterdam. The effectiveness of the game was assessed by measuring the change in knowledge about plasma and plasma donation from open-ended questions in a pen-and-paper questionnaire participants completed before and after playing the game. A Wilcoxon Signed-Rank Test revealed an increase in knowledge after playing the game, demonstrating that the game effectively educates players about plasma donation. No statistically significant relationship was found between knowledge increase and sociodemographic characteristics, nor with gameplay experiences. For educators and game designers, our game shows that even simple game designs and mechanics can be effective in imparting knowledge, while also preventing disparities in learning outcomes with respect to age, gender, and technical skills in playing games. For researchers, our study paves the way for a new line of research into the application of serious games in healthcare beyond clinical contexts, such as disease prevention or management. Importantly, our study highlights the potential of serious games to foster knowledge about health-related prosocial behaviours, possibly inspiring future research evaluating their potential as innovative teaching methods to address critical public health issues.

许多欧洲国家都面临着血浆短缺的问题，而缺乏对血浆捐献的认识和知识可能是导致捐献者人数较少的一个原因。提高对血浆的了解和认识的一种方法是通过非正式的教育方法，如严肃游戏。我们为荷兰的儿童和青少年（8-17 岁）开发了一款以血浆和血浆捐献为主题的严肃游戏，并与阿姆斯特丹 NEMO 科学博物馆合作，对 636 名参与者进行了测试。游戏的有效性是通过参与者在游戏前后填写的纸笔问卷中的开放式问题来衡量他们对血浆和血浆捐献知识的变化。Wilcoxon Signed-Rank 检验显示，玩游戏后，参与者的知识水平有所提高，这表明游戏有效地教育了参与者有关血浆捐献的知识。从统计学角度看，知识增长与社会人口特征和游戏体验之间没有明显关系。对于教育工作者和游戏设计者来说，我们的游戏表明，即使是简单的游戏设计和机制也能有效地传授知识，同时还能防止学习效果因年龄、性别和游戏技术技能而产生差异。对于研究人员来说，我们的研究为严肃游戏在医疗保健领域的应用开辟了新的研究方向，而不仅仅局限于临床环境，例如疾病预防或管理。重要的是，我们的研究强调了严肃游戏在培养与健康相关的亲社会行为知识方面的潜力，这可能会激发未来的研究，评估严肃游戏作为创新教学方法在解决关键公共卫生问题方面的潜力。

{"title":"Increasing knowledge about plasma and plasma donation through a serious game: Evidence from a mixed-method study","authors":"Alexandra Ciausescu , Eva-Maria Merz , Rene Bekkers , Arjen de Wit","doi":"10.1016/j.compedu.2025.105325","DOIUrl":"10.1016/j.compedu.2025.105325","url":null,"abstract":"<div><div>Many European countries are facing plasma shortages, with lack of awareness and knowledge about plasma donation being a potential explanation for low donor numbers. One approach to increasing knowledge and awareness about plasma is through informal educational methods, such as serious games. We developed a serious game focused on plasma and plasma donation for children and adolescents (8–17 years) in the Netherlands and tested it with 636 participants in collaboration with the science museum NEMO Amsterdam. The effectiveness of the game was assessed by measuring the change in knowledge about plasma and plasma donation from open-ended questions in a pen-and-paper questionnaire participants completed before and after playing the game. A Wilcoxon Signed-Rank Test revealed an increase in knowledge after playing the game, demonstrating that the game effectively educates players about plasma donation. No statistically significant relationship was found between knowledge increase and sociodemographic characteristics, nor with gameplay experiences. For educators and game designers, our game shows that even simple game designs and mechanics can be effective in imparting knowledge, while also preventing disparities in learning outcomes with respect to age, gender, and technical skills in playing games. For researchers, our study paves the way for a new line of research into the application of serious games in healthcare beyond clinical contexts, such as disease prevention or management. Importantly, our study highlights the potential of serious games to foster knowledge about health-related prosocial behaviours, possibly inspiring future research evaluating their potential as innovative teaching methods to address critical public health issues.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"233 ","pages":"Article 105325"},"PeriodicalIF":8.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Widening the Digital Divide: The mediating role of Intelligent Tutoring Systems in the relationship between rurality, socioeducational advantage, and mathematics learning outcomes

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-08 DOI: 10.1016/j.compedu.2025.105312

Brody Hannan , Rebecca Eynon

This study examines how the effects of school socioeducational advantage and rurality upon mathematics learning outcomes, are impacted by students’ usage of the ITS platform AdaptiveMath. Activity log data from the AdaptiveMath platform was merged with school sociodemographic data from the public MySchool database. The final analytic sample comprised of 66,451 Australian high school students across 304 schools in Years 7–10, who used the AdaptiveMath ITS platform in 2023. Structural Equation Modelling was employed to examine both the direct and indirect effects of school socioeducational advantage and rurality on student usage of the AdaptiveMath platform, and the resulting student learning outcomes.

This study finds marginal, but statistically significant relationships between ITS usage and learning outcomes, and the socioeducational advantage and rurality of a student's school. Students who are from more affluent and urban schools use the ITS platform earlier in their school career, for more years, and have higher learning outcomes than their rural, less affluent peers. Further, ITS usage was found to mediate the relationship between socioeducational advantage and rurality, such that it amplified the positive effects of socioeducational advantage, and the negative effects of rurality, upon learning outcomes.

The results suggest that introducing ITS platforms into Australian mathematics teaching will not reduce achievement gaps between affluent and disadvantaged schools. Rather, a Matthew Effect may be observed, whereby students attending privileged schools use ITS platforms more effectively, thereby contributing to an even greater disparities in learning outcome.

{"title":"Widening the Digital Divide: The mediating role of Intelligent Tutoring Systems in the relationship between rurality, socioeducational advantage, and mathematics learning outcomes","authors":"Brody Hannan , Rebecca Eynon","doi":"10.1016/j.compedu.2025.105312","DOIUrl":"10.1016/j.compedu.2025.105312","url":null,"abstract":"<div><div>This study examines how the effects of school socioeducational advantage and rurality upon mathematics learning outcomes, are impacted by students’ usage of the ITS platform AdaptiveMath. Activity log data from the AdaptiveMath platform was merged with school sociodemographic data from the public MySchool database. The final analytic sample comprised of 66,451 Australian high school students across 304 schools in Years 7–10, who used the AdaptiveMath ITS platform in 2023. Structural Equation Modelling was employed to examine both the direct and indirect effects of school socioeducational advantage and rurality on student usage of the AdaptiveMath platform, and the resulting student learning outcomes.</div><div>This study finds marginal, but statistically significant relationships between ITS usage and learning outcomes, and the socioeducational advantage and rurality of a student's school. Students who are from more affluent and urban schools use the ITS platform earlier in their school career, for more years, and have higher learning outcomes than their rural, less affluent peers. Further, ITS usage was found to mediate the relationship between socioeducational advantage and rurality, such that it amplified the positive effects of socioeducational advantage, and the negative effects of rurality, upon learning outcomes.</div><div>The results suggest that introducing ITS platforms into Australian mathematics teaching will not reduce achievement gaps between affluent and disadvantaged schools. Rather, a Matthew Effect may be observed, whereby students attending privileged schools use ITS platforms more effectively, thereby contributing to an even greater disparities in learning outcome.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"233 ","pages":"Article 105312"},"PeriodicalIF":8.9,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rapid in-class assessment of handwriting using a digital tablet: Multidimensional analysis of gender and socioeconomic status

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-04-04 DOI: 10.1016/j.compedu.2025.105311

Denis Pasco , Erik Gustafsson , Lucas Burget , Thibault Asselborn , Pierre Dillenbourg , Consortium LaMue , Marie Mazerolle

引用次数: 0

Exploring the prospects of multimodal large language models for Automated Emotion Recognition in education: Insights from Gemini

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-03-30 DOI: 10.1016/j.compedu.2025.105307

Shuzhen Yu , Alexey Androsov , Hanbing Yan

Emotions play a pivotal role in daily judgments and decision-making, particularly in educational settings, where understanding and responding to learners’ emotions is essential for personalized learning. While there has been growing interest in emotion recognition, traditional methods, such as manual observations and self-reports, are often subjective and time-consuming. The rise of AI has led to the development of Automated Emotion Recognition (AER), offering transformative opportunities for educational reform by enabling personalized learning through emotional insights. However, AER continues to face challenges, including reliance on large-scale labeled databases, limited flexibility, and inadequate adaptation to diverse educational contexts. Recent advancements in AI, particularly Multimodal Large Language Models (MLLMs), show promise in addressing these challenges, though their application in AER remains underexplored. This study aimed to fill this gap by systematically evaluating the performance of Gemini, a pioneering MLLM, in image-based AER tasks across five databases: CK+, FER-2013, RAF-DB, OL-SFED and DAiSEE. The analysis examined recognition accuracy, error patterns, emotion inference mechanisms, and the impact of image preprocessing techniques — such as face cropping, bilinear interpolation, and super-resolution — on the model’s performance. The results revealed that Gemini achieved high emotion recognition accuracy, especially in distinguishing emotional polarities across all databases. Image preprocessing significantly improved the recognition of basic emotions, though its effect on academic emotion recognition was minor. The confusion in academic emotion recognition stemmed from Gemini’s limited understanding of academic emotion features and its insufficient ability to capture contextual cues. Building on the results, this study outlines specific future research directions from both technological and educational perspectives. These findings offer valuable insights for advancing MLLMs in educational applications.

情绪在日常判断和决策中起着举足轻重的作用，尤其是在教育环境中，了解和应对学习者的情绪对个性化学习至关重要。虽然人们对情绪识别的兴趣与日俱增，但传统方法（如人工观察和自我报告）往往主观且耗时。人工智能的兴起促进了自动情感识别（AER）的发展，通过情感洞察实现个性化学习，为教育改革提供了变革机会。然而，自动情感识别仍然面临挑战，包括对大规模标签数据库的依赖、有限的灵活性以及对不同教育环境的适应性不足。人工智能领域的最新进展，尤其是多模态大语言模型（MLLMs），显示了应对这些挑战的前景，尽管它们在 AER 中的应用仍未得到充分探索。本研究旨在通过系统评估 Gemini（一种开创性的多模态大语言模型）在五个数据库中基于图像的 AER 任务中的表现来填补这一空白：CK+、FER-2013、RAF-DB、OL-SFED 和 DAiSEE。分析考察了识别准确率、错误模式、情感推理机制以及图像预处理技术（如人脸裁剪、双线性插值和超分辨率）对模型性能的影响。结果表明，Gemini 的情感识别准确率很高，尤其是在区分所有数据库中的情感极性方面。图像预处理大大提高了基本情绪的识别率，但对学术情绪识别的影响较小。学术情感识别方面的混乱源于 Gemini 对学术情感特征的理解有限，以及其捕捉上下文线索的能力不足。在研究结果的基础上，本研究从技术和教育两个角度概述了未来的具体研究方向。这些发现为推进 MLLM 在教育领域的应用提供了宝贵的见解。

{"title":"Exploring the prospects of multimodal large language models for Automated Emotion Recognition in education: Insights from Gemini","authors":"Shuzhen Yu , Alexey Androsov , Hanbing Yan","doi":"10.1016/j.compedu.2025.105307","DOIUrl":"10.1016/j.compedu.2025.105307","url":null,"abstract":"<div><div>Emotions play a pivotal role in daily judgments and decision-making, particularly in educational settings, where understanding and responding to learners’ emotions is essential for personalized learning. While there has been growing interest in emotion recognition, traditional methods, such as manual observations and self-reports, are often subjective and time-consuming. The rise of AI has led to the development of Automated Emotion Recognition (AER), offering transformative opportunities for educational reform by enabling personalized learning through emotional insights. However, AER continues to face challenges, including reliance on large-scale labeled databases, limited flexibility, and inadequate adaptation to diverse educational contexts. Recent advancements in AI, particularly Multimodal Large Language Models (MLLMs), show promise in addressing these challenges, though their application in AER remains underexplored. This study aimed to fill this gap by systematically evaluating the performance of Gemini, a pioneering MLLM, in image-based AER tasks across five databases: CK+, FER-2013, RAF-DB, OL-SFED and DAiSEE. The analysis examined recognition accuracy, error patterns, emotion inference mechanisms, and the impact of image preprocessing techniques — such as face cropping, bilinear interpolation, and super-resolution — on the model’s performance. The results revealed that Gemini achieved high emotion recognition accuracy, especially in distinguishing emotional polarities across all databases. Image preprocessing significantly improved the recognition of basic emotions, though its effect on academic emotion recognition was minor. The confusion in academic emotion recognition stemmed from Gemini’s limited understanding of academic emotion features and its insufficient ability to capture contextual cues. Building on the results, this study outlines specific future research directions from both technological and educational perspectives. These findings offer valuable insights for advancing MLLMs in educational applications.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"232 ","pages":"Article 105307"},"PeriodicalIF":8.9,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and implementation of a generative artificial intelligence-enhanced simulation to enhance problem-solving skills for pre-service teachers

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-03-25 DOI: 10.1016/j.compedu.2025.105306

Jieun Lim , Unggi Lee , Junbo Koh , Yeil Jeong , Yunseo Lee , Gyuri Byun , Haewon Jung , Yoonsun Jang , Sanghyeok Lee , Jewoong Moon

Effective teachers should be equipped to solve complex problems across diverse instructional and learning contexts. However, many teacher training programs struggle to bridge the gap between theoretical knowledge to real-world applications. The current study tackles this challenge by developing a generative artificial intelligence (GenAI)-enhanced simulation to improve preservice teachers’ problem-solving abilities. Using design-based research (DBR), we created a virtual environment that integrates problem-based learning (PBL) with GenAI technology. The simulation was rigorously refined through expert review and usability testing before being implemented in a teacher training program. We evaluated its effectiveness by comparing three groups: (1) a text-based scenario, (2) a rule-based simulation, and (3) a GenAI-enhanced simulation. Pre- and post-test results showed significant improvements in problem-solving skills for both the rule-based and GenAI-enhanced simulation groups compared to the text-based scenario group. Notably, qualitative findings revealed that students reported heightened realism and immersion in the GenAI-enhanced simulation, attributing this to more dynamic interactions with AI agents that helped them better contextualize PBL and increased their motivation. Our study findings contribute design principles for developing GenAI-enhanced simulations in teacher education, offering promising insights into leveraging AI technology to create more engaging and effective training experiences.

{"title":"Development and implementation of a generative artificial intelligence-enhanced simulation to enhance problem-solving skills for pre-service teachers","authors":"Jieun Lim , Unggi Lee , Junbo Koh , Yeil Jeong , Yunseo Lee , Gyuri Byun , Haewon Jung , Yoonsun Jang , Sanghyeok Lee , Jewoong Moon","doi":"10.1016/j.compedu.2025.105306","DOIUrl":"10.1016/j.compedu.2025.105306","url":null,"abstract":"<div><div>Effective teachers should be equipped to solve complex problems across diverse instructional and learning contexts. However, many teacher training programs struggle to bridge the gap between theoretical knowledge to real-world applications. The current study tackles this challenge by developing a generative artificial intelligence <strong>(</strong>GenAI)-enhanced simulation to improve preservice teachers’ problem-solving abilities. Using design-based research (DBR), we created a virtual environment that integrates problem-based learning (PBL) with GenAI technology. The simulation was rigorously refined through expert review and usability testing before being implemented in a teacher training program. We evaluated its effectiveness by comparing three groups: (1) a text-based scenario, (2) a rule-based simulation, and (3) a GenAI-enhanced simulation. Pre- and post-test results showed significant improvements in problem-solving skills for both the rule-based and GenAI-enhanced simulation groups compared to the text-based scenario group. Notably, qualitative findings revealed that students reported heightened realism and immersion in the GenAI-enhanced simulation, attributing this to more dynamic interactions with AI agents that helped them better contextualize PBL and increased their motivation. Our study findings contribute design principles for developing GenAI-enhanced simulations in teacher education, offering promising insights into leveraging AI technology to create more engaging and effective training experiences.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"232 ","pages":"Article 105306"},"PeriodicalIF":8.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling student teachers’ self-regulated learning of complex professional knowledge: A sequential and clustering analysis with think-aloud protocols

IF 8.9 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education

Pub Date : 2025-03-25 DOI: 10.1016/j.compedu.2025.105310

Lingyun Huang , Ying Zhan , Shen Ba

There has been much discussion regarding the positive relationship between self-regulated learning (SRL) and technological pedagogical content knowledge (TPACK) development for student teachers. This study continued this claim and adopted advanced analytical methods to explain how SRL influences TPACK learning. Think-aloud protocols from 39 participants were collected and transcribed when they were learning TPACK by designing technology-infused lessons with nBrowser, a computer-based learning environment. Based on models, nine critical SRL events were retrieved from participants‘ think-aloud protocols and analyzed through sequential clustering analysis. The results show two SRL groups indicating distinct self-regulatory sequential patterns. One group had a shorter sequence length and dominantly enacted elaboration activities (Low-SRL group), while the other had longer sequence lengths and engaged in diverse SRL activities (High-regulation group). Relating to TPACK performance indicated by the quality of lesson plans, the results reveal that the participants in the High-SRL group outperformed their counterparts in the Low-SRL group. The findings are consistent with previous evidence and provide implications for practitioners about the importance of student teachers’ self-regulation trajectories.

{"title":"Modeling student teachers’ self-regulated learning of complex professional knowledge: A sequential and clustering analysis with think-aloud protocols","authors":"Lingyun Huang , Ying Zhan , Shen Ba","doi":"10.1016/j.compedu.2025.105310","DOIUrl":"10.1016/j.compedu.2025.105310","url":null,"abstract":"<div><div>There has been much discussion regarding the positive relationship between self-regulated learning (SRL) and technological pedagogical content knowledge (TPACK) development for student teachers. This study continued this claim and adopted advanced analytical methods to explain how SRL influences TPACK learning. Think-aloud protocols from 39 participants were collected and transcribed when they were learning TPACK by designing technology-infused lessons with nBrowser, a computer-based learning environment. Based on models, nine critical SRL events were retrieved from participants‘ think-aloud protocols and analyzed through sequential clustering analysis. The results show two SRL groups indicating distinct self-regulatory sequential patterns. One group had a shorter sequence length and dominantly enacted elaboration activities (Low-SRL group), while the other had longer sequence lengths and engaged in diverse SRL activities (High-regulation group). Relating to TPACK performance indicated by the quality of lesson plans, the results reveal that the participants in the High-SRL group outperformed their counterparts in the Low-SRL group. The findings are consistent with previous evidence and provide implications for practitioners about the importance of student teachers’ self-regulation trajectories.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"233 ","pages":"Article 105310"},"PeriodicalIF":8.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0