Feedback Design and Student Participation Enhancement Strategies in Software-Assisted History Teaching System

The integration of software-assisted systems in history teaching requires effective feedback mechanisms and student participation strategies. Variations in student behavior and participation may also affect the generalization of the results. This research investigates the integration of the Adaptive Black-winged Kite Algorithm tuned Modified Decision Tree (ABK-MDT) for optimizing feedback design and enhancing student participation in software-assisted history teaching systems. Data are collected from software-assisted history teaching systems, capturing student interactions, feedback responses, participation levels, and performance metrics, assuring a rich dataset for simulation assessment. Cleaning, eliminating outliers, dealing with missing numbers, normalizing, and scaling numerical characteristics are all part of data preparation to ensure consistency and improve the effectiveness of the machine learning model in predicting student participation and feedback effectiveness. ABK algorithm that optimizes MDT parameters improves the predictive accuracy of student participation and feedback response in the software-assisted learning system. The method is implemented in Python, achieving promising results with precision (92.1%), recall (92.6%), F1-Score (91.9%), and accuracy (93.6%), indicating strong predictive capabilities and robust model performance in feedback optimization and participation enhancement. The ABK-MDT algorithm significantly enhances student participation and feedback systems in software-assisted history education, offering valuable insights for future educational technology development.