Enhancing student academic performance in middle school classrooms by fostering engagement motivation through intelligent assessment of teacher praise emotional intensity
Zengzhao Chen , Debo Ren , Zhifeng Wang , Lu Gao , Yawen Shi , Hai Liu , Tonglian Yang
{"title":"Enhancing student academic performance in middle school classrooms by fostering engagement motivation through intelligent assessment of teacher praise emotional intensity","authors":"Zengzhao Chen , Debo Ren , Zhifeng Wang , Lu Gao , Yawen Shi , Hai Liu , Tonglian Yang","doi":"10.1016/j.learninstruc.2025.102185","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Teacher praise is a powerful tool for enhancing student learning and managing behavioral challenges. However, existing methods for assessing teacher praise are overly simplistic, typically only relying on the frequency of behavioral special praise (BSP) to judge its effectiveness. Teacher praise serves as a means of conveying emotion, we categorized it according to emotional intensity. This approach seeks to examine how enhancing the intensity of praise influences student learning.</div></div><div><h3>Aimed</h3><div>The core research objectives are: (1) to explore the classification of praise intensity; (2) to investigate whether the GPT tool can effectively influence teachers' praise intensity; and (3) to examine the direct and indirect effects of changes in praise intensity on student academic performance.</div></div><div><h3>Method</h3><div>This study developed a praise intensity recognition assistant using GPT-3.5. A praise dataset was constructed and fine-tuned, achieving an accuracy of 95 %, demonstrating effective recognition. However, detecting and enhancing praise intensity remains a challenge.</div></div><div><h3>Sample</h3><div>20 teachers and 523 students participated in an intervention experiment focusing on praise intensity. Over a three-month period, we used this tool to observe whether improvements in teacher praise intensity affected student academic performance and learning behavior.</div></div><div><h3>Result</h3><div>Findings revealed that while student academic performance showed no significant improvement, student engagement notably increased.</div></div><div><h3>Conclusion</h3><div>Student engagement acted as a mediator, indicating an indirect link between teacher praise intensity and academic performance. This study underscores the indirect influence of enhanced praise intensity facilitated by GPT, highlighting the crucial role of student engagement in this process.</div></div>","PeriodicalId":48357,"journal":{"name":"Learning and Instruction","volume":"99 ","pages":"Article 102185"},"PeriodicalIF":4.7000,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Learning and Instruction","FirstCategoryId":"95","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0959475225001094","RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Teacher praise is a powerful tool for enhancing student learning and managing behavioral challenges. However, existing methods for assessing teacher praise are overly simplistic, typically only relying on the frequency of behavioral special praise (BSP) to judge its effectiveness. Teacher praise serves as a means of conveying emotion, we categorized it according to emotional intensity. This approach seeks to examine how enhancing the intensity of praise influences student learning.
Aimed
The core research objectives are: (1) to explore the classification of praise intensity; (2) to investigate whether the GPT tool can effectively influence teachers' praise intensity; and (3) to examine the direct and indirect effects of changes in praise intensity on student academic performance.
Method
This study developed a praise intensity recognition assistant using GPT-3.5. A praise dataset was constructed and fine-tuned, achieving an accuracy of 95 %, demonstrating effective recognition. However, detecting and enhancing praise intensity remains a challenge.
Sample
20 teachers and 523 students participated in an intervention experiment focusing on praise intensity. Over a three-month period, we used this tool to observe whether improvements in teacher praise intensity affected student academic performance and learning behavior.
Result
Findings revealed that while student academic performance showed no significant improvement, student engagement notably increased.
Conclusion
Student engagement acted as a mediator, indicating an indirect link between teacher praise intensity and academic performance. This study underscores the indirect influence of enhanced praise intensity facilitated by GPT, highlighting the crucial role of student engagement in this process.
期刊介绍:
As an international, multi-disciplinary, peer-refereed journal, Learning and Instruction provides a platform for the publication of the most advanced scientific research in the areas of learning, development, instruction and teaching. The journal welcomes original empirical investigations. The papers may represent a variety of theoretical perspectives and different methodological approaches. They may refer to any age level, from infants to adults and to a diversity of learning and instructional settings, from laboratory experiments to field studies. The major criteria in the review and the selection process concern the significance of the contribution to the area of learning and instruction, and the rigor of the study.