Enhancing student academic performance in middle school classrooms by fostering engagement motivation through intelligent assessment of teacher praise emotional intensity

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. © 2025 Elsevier Ltd

Keywords

Author Keywords

Student academic performance Student engagement emotional intensity GPT assistant Teacher praise intensity

Index Keywords

Author Affiliations

Central China Normal University, Wuhan, Hubei, China

Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, Hubei, China

Funding & Acknowledgements

Central China Normal University, CCNU

Grant: CCNUai013, CCNU25ai011

We are grateful to the instructors and students who participated in the video recordings, as well as all those who contributed to the completion of this paper. This work was supported by the National Natural Science Foundation of China (No. 62477022, 62177022, 62277026), the Independent Research Project of Central China Normal University (No. CCNUai013, CCNU25ai011), and the Research Project of the National Collaborative Innovation Experimental Base for Teacher Development of Central China Normal University (No. CCNUTEIII 2021\u201321).

Central China Normal University, CCNU

We are grateful to the instructors and students who participated in the video recordings, as well as all those who contributed to the completion of this paper. This work was supported by the National Natural Science Foundation of China (No. 62477022, 62177022, 62277026), the Independent Research Project of Central China Normal University (No. CCNUai013, CCNU25ai011), and the Research Project of the National Collaborative Innovation Experimental Base for Teacher Development of Central China Normal University (No. CCNUTEIII 2021\u201321).

National Natural Science Foundation of China, NNSFC

Grant: 62477022, 62277026, 62177022

We are grateful to the instructors and students who participated in the video recordings, as well as all those who contributed to the completion of this paper. This work was supported by the National Natural Science Foundation of China (No. 62477022, 62177022, 62277026), the Independent Research Project of Central China Normal University (No. CCNUai013, CCNU25ai011), and the Research Project of the National Collaborative Innovation Experimental Base for Teacher Development of Central China Normal University (No. CCNUTEIII 2021\u201321).

National Natural Science Foundation of China, NNSFC

We are grateful to the instructors and students who participated in the video recordings, as well as all those who contributed to the completion of this paper. This work was supported by the National Natural Science Foundation of China (No. 62477022, 62177022, 62277026), the Independent Research Project of Central China Normal University (No. CCNUai013, CCNU25ai011), and the Research Project of the National Collaborative Innovation Experimental Base for Teacher Development of Central China Normal University (No. CCNUTEIII 2021\u201321).

References 10 References

1 Interactive Learning Environments, (2023)

2 Behavioral Disorders, (2012)

3 Anderson, Rajen A., A Theory of Moral Praise, Trends in Cognitive Sciences, 24, 9, pp. 694-703, (2020)

4 Elementary School Journal, (1979)

5 Appleton, James J., Measuring cognitive and psychological engagement: Validation of the Student Engagement Instrument, Journal of School Psychology, 44, 5, pp. 427-445, (2006)

6 Engagement and Dropping Out of School A Life Course Perspective, (2001)

7 Basit, Tehmina N., Manual or electronic? The role of coding in qualitative data analysis, Educational Research, 45, 2, pp. 143-154, (2003)

8 Baumeister, Roy F., Does High Self-Esteem Cause Better Performance, Interpersonal Success, Happiness, or Healthier Lifestyles?, Psychological Science in the Public Interest, 4, 1, pp. 1-44, (2003)

9 Bayat, Mojdeh, Clarifying Issues Regarding the Use of Praise With Young Children, Topics in Early Childhood Special Education, 31, 2, pp. 121-128, (2011)

10 Bear, George G., Differences in classroom removals and use of praise and rewards in American, Chinese, and Japanese schools, Teaching and Teacher Education, 53, pp. 41-50, (2016)

Enhancing student academic performance in middle school classrooms by fostering engagement motivation through intelligent assessment of teacher praise emotional intensity

How to Cite