Pub Date : 2025-09-01Epub Date: 2025-06-09DOI: 10.1016/j.stueduc.2025.101478
Xin Ma , Yanhong Zhang , Malar San , Aye Myint Than Htay , Jing Yuan
Using Myanmar national sample (5707 students from 202 schools) from 2019 Southeast Asia Primary Learning Metrics, this study discovered unique effects of home language on academic achievement at levels of homes and schools, after control of student and school characteristics. Against the background finding that schools were significantly responsible for academic achievement, there was a lack of interaction effects between socioeconomic status (SES) and speaking Myanmar versus non-Myanmar at home as well as interaction effects between school mean SES and within-school proportion of students speaking Myanmar at home across academic achievement in mathematics, reading, and writing. Speaking Myanmar at a home resulted in significant academic advantage at the home level across mathematics, reading, and writing. Over and above, a higher proportion of students speaking Myanmar at home within a school resulted in significant academic advantage at the school level across reading and writing.
{"title":"Unique effects of home language on academic achievement among Myanmar students: A home and school perspective","authors":"Xin Ma , Yanhong Zhang , Malar San , Aye Myint Than Htay , Jing Yuan","doi":"10.1016/j.stueduc.2025.101478","DOIUrl":"10.1016/j.stueduc.2025.101478","url":null,"abstract":"<div><div>Using Myanmar national sample (5707 students from 202 schools) from 2019 Southeast Asia Primary Learning Metrics, this study discovered unique effects of home language on academic achievement at levels of homes and schools, after control of student and school characteristics. Against the background finding that schools were significantly responsible for academic achievement, there was a lack of interaction effects between socioeconomic status (SES) and speaking Myanmar versus non-Myanmar at home as well as interaction effects between school mean SES and within-school proportion of students speaking Myanmar at home across academic achievement in mathematics, reading, and writing. Speaking Myanmar at a home resulted in significant academic advantage at the home level across mathematics, reading, and writing. <em>Over and above</em>, a higher proportion of students speaking Myanmar at home within a school resulted in significant academic advantage at the school level across reading and writing.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101478"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144241036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-06-20DOI: 10.1016/j.stueduc.2025.101480
Xue Yin , Kun Dou
This study investigates the effects of an AI-assisted critical thinking (CT)-oriented writing intervention supported with ChatGPT involving 250 undergraduate EFL learners from three public universities. The research measured changes in students’ writing proficiency and their acceptance of ChatGPT in CT-oriented writing practices. A pretest-posttest design was adopted, with data collected through pre-post-writing tests (n = 250), an acceptance questionnaire (n = 250), and further semi-structured interviews (n = 25). The writing tests were evaluated across nine dimensions: clarity, accuracy, precision, relevance, depth, breadth, logic, significance, and fairness. The acceptance questionnaire, grounded in the Extended Unified Theory of Acceptance and Use of Technology (UTAUT2) model, assessed six constructs, i.e., performance expectancy, effort expectancy, hedonic motivation, habit, trust, and behavioral intention. The results showed that 1) The intervention significantly enhanced students’ CT reflected in writing; 2) Positive shifts were observed in four scales of ChatGPT acceptance in a CT-oriented writing context, i.e., performance expectancy, effort expectancy, trust, and behavior intention, though only marginal increase in hedonic motivation and habit. Meanwhile, the study identified the primary aspects of ChatGPT influencing EFL learners’ CT-oriented writing. These results demonstrate the potential of ChatGPT as a scaffolding tool for CT-oriented writing training in EFL contexts. Despite limitations such as the single-group experimental design and 8-week experimental period, the findings offer valuable insights for further research and development in AI-driven tools in EFL writing pedagogy. Future research could adopt a multi-group design and longitudinal assessments to further validate the intervention’s sustained effects.
{"title":"An AI-assisted critical thinking intervention to enhance undergraduate EFL learners’ writing proficiency","authors":"Xue Yin , Kun Dou","doi":"10.1016/j.stueduc.2025.101480","DOIUrl":"10.1016/j.stueduc.2025.101480","url":null,"abstract":"<div><div>This study investigates the effects of an AI-assisted critical thinking (CT)-oriented writing intervention supported with ChatGPT involving 250 undergraduate EFL learners from three public universities. The research measured changes in students’ writing proficiency and their acceptance of ChatGPT in CT-oriented writing practices. A pretest-posttest design was adopted, with data collected through pre-post-writing tests (n = 250), an acceptance questionnaire (n = 250), and further semi-structured interviews (n = 25). The writing tests were evaluated across nine dimensions: clarity, accuracy, precision, relevance, depth, breadth, logic, significance, and fairness. The acceptance questionnaire, grounded in the Extended Unified Theory of Acceptance and Use of Technology (UTAUT2) model, assessed six constructs, i.e., performance expectancy, effort expectancy, hedonic motivation, habit, trust, and behavioral intention. The results showed that 1) The intervention significantly enhanced students’ CT reflected in writing; 2) Positive shifts were observed in four scales of ChatGPT acceptance in a CT-oriented writing context, i.e., performance expectancy, effort expectancy, trust, and behavior intention, though only marginal increase in hedonic motivation and habit. Meanwhile, the study identified the primary aspects of ChatGPT influencing EFL learners’ CT-oriented writing. These results demonstrate the potential of ChatGPT as a scaffolding tool for CT-oriented writing training in EFL contexts. Despite limitations such as the single-group experimental design and 8-week experimental period, the findings offer valuable insights for further research and development in AI-driven tools in EFL writing pedagogy. Future research could adopt a multi-group design and longitudinal assessments to further validate the intervention’s sustained effects.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101480"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study explores teachers’ conceptions, experiences, and learning needs regarding the important 21st-century teaching skill of promoting student reflection through process-oriented feedback. Interviewing 23 secondary school teachers about their perceived practices and challenges identified four groups: Basic, Intermediate, Advanced, and Constrained. The Basic group teachers struggled with concepts of process-oriented feedback and reflection, hindering the provision of effective reflection tasks and feedback. The Intermediate group teachers faced difficulties with increasing reflection task frequency and providing weekly feedback. The Advanced group teachers, with extensive experience, still struggled with implementing cyclical reflection on school level. The Constrained group teachers encountered external limitations like limited lesson hours and lack of support. Learning needs varied among the teachers’ groups, emphasizing the importance of tailored professional development programs to enhance teachers' process-oriented feedback literacy. Findings contribute to understanding stages of effective teaching and their implications for teacher evaluation towards stage-geared professional development of teaching skills.
{"title":"Promoting students’ reflection through process-oriented feedback: Teachers’ conceptions, practices and learning needs","authors":"J.J.H. Görtzen, S.H.M. Stollman, G.L.M. Schellings, J.D. Vermunt, N.M. Nieveen","doi":"10.1016/j.stueduc.2025.101483","DOIUrl":"10.1016/j.stueduc.2025.101483","url":null,"abstract":"<div><div>This study explores teachers’ conceptions, experiences, and learning needs regarding the important 21st-century teaching skill of promoting student reflection through process-oriented feedback. Interviewing 23 secondary school teachers about their perceived practices and challenges identified four groups: Basic, Intermediate, Advanced, and Constrained. The Basic group teachers struggled with concepts of process-oriented feedback and reflection, hindering the provision of effective reflection tasks and feedback. The Intermediate group teachers faced difficulties with increasing reflection task frequency and providing weekly feedback. The Advanced group teachers, with extensive experience, still struggled with implementing cyclical reflection on school level. The Constrained group teachers encountered external limitations like limited lesson hours and lack of support. Learning needs varied among the teachers’ groups, emphasizing the importance of tailored professional development programs to enhance teachers' process-oriented feedback literacy. Findings contribute to understanding stages of effective teaching and their implications for teacher evaluation towards stage-geared professional development of teaching skills.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101483"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-05-17DOI: 10.1016/j.stueduc.2025.101474
Nurullah Eryilmaz , Alec I. Kennedy , Rolf Strietholt , Stefan Johansson
Teacher job satisfaction is considered a crucial factor in retaining successful teachers in the workforce and for the general well-being of teachers. Understanding the relationship between school working conditions with job satisfaction is considered to be essential for enhancing teacher motivation, retention, and ultimately, student outcomes. Following the influential study by Toropova et al. (2021), the current study employs regression analysis of TIMSS 2019 data from 46 countries and benchmarking entities to investigate the relationship between school working conditions – school leadership, student discipline, and teacher workload – and teacher job satisfaction among secondary school teachers. The findings shed light on the specific aspects of school working conditions that are significantly associated with teacher job satisfaction. The findings highlight a notable association between leadership support and student discipline with teacher job satisfaction in various countries. Furthermore, our findings indicate that, on average, female teachers report higher job satisfaction than male teachers across most countries, although country-specific workforce compositions may play a role in shaping this relationship, and professional development was found to be positively correlated with teacher job satisfaction. The effects of years of teaching experience, majoring in mathematics, and majoring in mathematics education yielded inconsistent results. The results contribute to the existing research on teacher job satisfaction and provide practical implications for policymakers, school administrators, and educational stakeholders to create supportive and conducive working environments for teachers and contribute to the professional well-being of teachers worldwide.
{"title":"Teacher job satisfaction: International evidence on the role of school working conditions and teacher characteristics","authors":"Nurullah Eryilmaz , Alec I. Kennedy , Rolf Strietholt , Stefan Johansson","doi":"10.1016/j.stueduc.2025.101474","DOIUrl":"10.1016/j.stueduc.2025.101474","url":null,"abstract":"<div><div>Teacher job satisfaction is considered a crucial factor in retaining successful teachers in the workforce and for the general well-being of teachers. Understanding the relationship between school working conditions with job satisfaction is considered to be essential for enhancing teacher motivation, retention, and ultimately, student outcomes. Following the influential study by Toropova et al. (2021), the current study employs regression analysis of TIMSS 2019 data from 46 countries and benchmarking entities to investigate the relationship between school working conditions – school leadership, student discipline, and teacher workload – and teacher job satisfaction among secondary school teachers. The findings shed light on the specific aspects of school working conditions that are significantly associated with teacher job satisfaction. The findings highlight a notable association between leadership support and student discipline with teacher job satisfaction in various countries. Furthermore, our findings indicate that, on average, female teachers report higher job satisfaction than male teachers across most countries, although country-specific workforce compositions may play a role in shaping this relationship, and professional development was found to be positively correlated with teacher job satisfaction. The effects of years of teaching experience, majoring in mathematics, and majoring in mathematics education yielded inconsistent results. The results contribute to the existing research on teacher job satisfaction and provide practical implications for policymakers, school administrators, and educational stakeholders to create supportive and conducive working environments for teachers and contribute to the professional well-being of teachers worldwide.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101474"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-08-01DOI: 10.1016/j.stueduc.2025.101494
Aron Decuyper , Mathea Simons , Ruben Vanderlinde
While effective teaching behaviour is crucial for students’ academic outcomes, little research has been conducted on it in team teaching. The limited research is primarily based on self-reported data from teachers, which may not fully capture actual teaching practices. This qualitative study addresses this gap by employing video-based observation data from twelve teams engaged in team teaching. The ICALT observation instrument (Van de Grift, 2007) is used to assess teachers’ (n = 27) effective teaching behaviour in team teaching. The findings indicate that teachers generally exhibit effective teaching behaviour during team teaching. Moreover, through horizontal and vertical analysis, the study identifies three distinct categories of teams based on their degree of effective teaching behaviour: (1) struggling, (2) complementary, and (3) excelling teams. These findings provide valuable insights into the nuances of team dynamics and their impact on teaching effectiveness.
虽然有效的教学行为对学生的学业成绩至关重要，但在团队教学中对其进行的研究却很少。有限的研究主要基于教师的自我报告数据，可能无法完全捕捉实际的教学实践。本定性研究通过采用来自12个从事团队教学的团队的基于视频的观察数据来解决这一差距。采用ICALT观察仪（Van de Grift, 2007）评估教师（n = 27）在团队教学中的有效教学行为。研究结果表明，教师在团队教学中普遍表现出有效的教学行为。此外，通过横向和纵向分析，该研究根据有效教学行为的程度确定了三种不同类型的团队：(1)挣扎型团队，(2)互补型团队和(3)卓越型团队。这些发现为团队动态的细微差别及其对教学效果的影响提供了有价值的见解。
{"title":"Teachers’ effective teaching behaviour during team teaching: A video-based observation study","authors":"Aron Decuyper , Mathea Simons , Ruben Vanderlinde","doi":"10.1016/j.stueduc.2025.101494","DOIUrl":"10.1016/j.stueduc.2025.101494","url":null,"abstract":"<div><div>While effective teaching behaviour is crucial for students’ academic outcomes, little research has been conducted on it in team teaching. The limited research is primarily based on self-reported data from teachers, which may not fully capture actual teaching practices. This qualitative study addresses this gap by employing video-based observation data from twelve teams engaged in team teaching. The ICALT observation instrument (<span><span>Van de Grift, 2007</span></span>) is used to assess teachers’ (n = 27) effective teaching behaviour in team teaching. The findings indicate that teachers generally exhibit effective teaching behaviour during team teaching. Moreover, through horizontal and vertical analysis, the study identifies three distinct categories of teams based on their degree of effective teaching behaviour: (1) struggling, (2) complementary, and (3) excelling teams. These findings provide valuable insights into the nuances of team dynamics and their impact on teaching effectiveness.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101494"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144749359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-06-28DOI: 10.1016/j.stueduc.2025.101482
Jannika Lindvall , Nils Kirsten , Andreas Ryve , Jan-Eric Gustafsson
In this review, we map and summarize studies examining the effects of teachers’ participation in professional development (PD) on teaching practices and student achievement based on nationally representative datasets, reflecting both the teacher population and the PD they typically receive. We also critically assess the statistical approaches used in these studies to evaluate the credibility and robustness of their findings. The reviewed studies demonstrate that large-scale datasets (e.g., TIMSS and NAEP) offer valuable opportunities to study PD in representative settings. However, only a minority of the studies adequately address the methodological challenges associated with these datasets. As a result, while our meta-analysis indicates that PD participation correlates with teaching practices and student achievement, we caution against interpreting these results as causal due to methodological limitations in most of the reviewed studies. Finally, we propose strategies for future research to produce more credible results.
{"title":"A critical review and meta-analysis of studies investigating the effects of the professional development teachers typically receive","authors":"Jannika Lindvall , Nils Kirsten , Andreas Ryve , Jan-Eric Gustafsson","doi":"10.1016/j.stueduc.2025.101482","DOIUrl":"10.1016/j.stueduc.2025.101482","url":null,"abstract":"<div><div>In this review, we map and summarize studies examining the effects of teachers’ participation in professional development (PD) on teaching practices and student achievement based on nationally representative datasets, reflecting both the teacher population and the PD they typically receive. We also critically assess the statistical approaches used in these studies to evaluate the credibility and robustness of their findings. The reviewed studies demonstrate that large-scale datasets (e.g., TIMSS and NAEP) offer valuable opportunities to study PD in representative settings. However, only a minority of the studies adequately address the methodological challenges associated with these datasets. As a result, while our meta-analysis indicates that PD participation correlates with teaching practices and student achievement, we caution against interpreting these results as causal due to methodological limitations in most of the reviewed studies. Finally, we propose strategies for future research to produce more credible results.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101482"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Substantial evidence shows that high-quality early childhood education and care (ECEC) positively affects children's development. However, many ECEC settings do not meet these standards, highlighting the need for professional development (PD) programs for staff. There is limited knowledge about effective PD models from the Nordic context, particularly in areas with large multiethnic, multilingual populations, and low-income families. The OEES study, involving 89 toddler and 125 preschool classrooms across 56 Norwegian ECEC centers, examined the impact of a teacher PD program on teacher–child interaction quality using the CLASS tool, compared to a control group over 18 months. Results indicate that OEES effectively improves teacher–child interactions, especially in toddler classrooms.
{"title":"Promoting classroom quality through professional development: Results from the Oslo early education study, a randomized controlled trial","authors":"Ratib Lekhal , Lisa Karlsen , Tiril Wilhelmsen , Deborah Lowe Vandell , Stian Lydersen , Veslemøy Rydland","doi":"10.1016/j.stueduc.2025.101462","DOIUrl":"10.1016/j.stueduc.2025.101462","url":null,"abstract":"<div><div>Substantial evidence shows that high-quality early childhood education and care (ECEC) positively affects children's development. However, many ECEC settings do not meet these standards, highlighting the need for professional development (PD) programs for staff. There is limited knowledge about effective PD models from the Nordic context, particularly in areas with large multiethnic, multilingual populations, and low-income families. The OEES study, involving 89 toddler and 125 preschool classrooms across 56 Norwegian ECEC centers, examined the impact of a teacher PD program on teacher–child interaction quality using the CLASS tool, compared to a control group over 18 months. Results indicate that OEES effectively improves teacher–child interactions, especially in toddler classrooms.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"86 ","pages":"Article 101462"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-01Epub Date: 2025-03-24DOI: 10.1016/j.stueduc.2025.101457
Ali Karakaş , Ceyhun Yükselir
This study explored the role of peer and instructor feedback on pre-service EFL teachers’ reflection types and levels during a video-mediated microteaching process. While previous research has examined various aspects of reflection and feedback in teacher education, there is currently a lack of studies specifically investigating how instructor and peer feedback shape the types and levels of reflection pre-service teachers engage in through video-mediated microteaching in the EFL context. The participants included 34 third-grade pre-service EFL teachers who performed weekly microteaching sessions. Data collected via qualitative tools were analysed through thematic analysis. Participants initially lacked critical engagement in reflection, focusing primarily on content delivery. However, they became more evaluative in their reflections by engaging in process and premise reflections, particularly in the post-video phase, as a result of listening to recorded teacher and peer feedback and engaging in group discussions. The findings suggest that while microteaching alone was insufficient for fostering deep reflection, the combination of video recordings and constructive peer and instructor feedback guided pre-service teachers towards higher levels of reflection, such as analytical and critical/evaluative reflection. The study highlights the importance of structured feedback opportunities in teacher education programs to cultivate habits of ongoing professional growth among pre-service teachers.
{"title":"Peer and instructor feedback on pre-service EFL teachers’ reflection types and levels in video-mediated microteaching","authors":"Ali Karakaş , Ceyhun Yükselir","doi":"10.1016/j.stueduc.2025.101457","DOIUrl":"10.1016/j.stueduc.2025.101457","url":null,"abstract":"<div><div>This study explored the role of peer and instructor feedback on pre-service EFL teachers’ reflection types and levels during a video-mediated microteaching process. While previous research has examined various aspects of reflection and feedback in teacher education, there is currently a lack of studies specifically investigating how instructor and peer feedback shape the types and levels of reflection pre-service teachers engage in through video-mediated microteaching in the EFL context. The participants included 34 third-grade pre-service EFL teachers who performed weekly microteaching sessions. Data collected via qualitative tools were analysed through thematic analysis. Participants initially lacked critical engagement in reflection, focusing primarily on content delivery. However, they became more evaluative in their reflections by engaging in process and premise reflections, particularly in the post-video phase, as a result of listening to recorded teacher and peer feedback and engaging in group discussions. The findings suggest that while microteaching alone was insufficient for fostering deep reflection, the combination of video recordings and constructive peer and instructor feedback guided pre-service teachers towards higher levels of reflection, such as analytical and critical/evaluative reflection. The study highlights the importance of structured feedback opportunities in teacher education programs to cultivate habits of ongoing professional growth among pre-service teachers.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"85 ","pages":"Article 101457"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143685892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-06-01Epub Date: 2025-04-18DOI: 10.1016/j.stueduc.2025.101463
Alexander Karl Ferdinand Loder
The strategy process of universities can span several years into the future with prediction of student performance being an important aspect for university governance. “Micro Cluster Learning” is proposed, by applying a hybrid of machine learning and ARIMA models to micro clusters of a university’s administrative data. The aim was to predict a performance indicator one to three academic years in the future and to compare the results of five years and to official statistics. Micro clusters were generated and a stack of 20 machine learning algorithms was applied to each cluster. The algorithms and their hyperparameter settings were determined in an explorative manual pre-selection process. The results show deviations from the official statistics between 2 % and 8 % (SD = 6 %) for one academic year in the future, 1–29 % (SD = 19 %) for two and 1–17 % (SD = 11 %) for three years. Model performance correlated with increasing details in the micro clusters and was better in larger micro clusters. The method is very flexible and can be used in a multitude of different university settings worldwide and for different outcomes of interest, e.g., grades or student status. However, the flexibility goes along with a tedious setup and very long runtimes. Future improvements with increased automation are warranted and “meta-procedures” should be developed that can perform automated resampling and hyperparameter tuning on a stack of algorithms. The method presented in this study contributes to preventive university management in different countries and university systems.
{"title":"Machine learning for university management: Micro Cluster Learning to predict \"active\" students","authors":"Alexander Karl Ferdinand Loder","doi":"10.1016/j.stueduc.2025.101463","DOIUrl":"10.1016/j.stueduc.2025.101463","url":null,"abstract":"<div><div>The strategy process of universities can span several years into the future with prediction of student performance being an important aspect for university governance. “Micro Cluster Learning” is proposed, by applying a hybrid of machine learning and ARIMA models to micro clusters of a university’s administrative data. The aim was to predict a performance indicator one to three academic years in the future and to compare the results of five years and to official statistics. Micro clusters were generated and a stack of 20 machine learning algorithms was applied to each cluster. The algorithms and their hyperparameter settings were determined in an explorative manual pre-selection process. The results show deviations from the official statistics between 2 % and 8 % (<em>SD</em> = 6 %) for one academic year in the future, 1–29 % (<em>SD</em> = 19 %) for two and 1–17 % (<em>SD</em> = 11 %) for three years. Model performance correlated with increasing details in the micro clusters and was better in larger micro clusters. The method is very flexible and can be used in a multitude of different university settings worldwide and for different outcomes of interest, e.g., grades or student status. However, the flexibility goes along with a tedious setup and very long runtimes. Future improvements with increased automation are warranted and “meta-procedures” should be developed that can perform automated resampling and hyperparameter tuning on a stack of algorithms. The method presented in this study contributes to preventive university management in different countries and university systems.</div></div>","PeriodicalId":47539,"journal":{"name":"Studies in Educational Evaluation","volume":"85 ","pages":"Article 101463"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号