An Innovative Approach to Automatically Generating Derivative Questions for Calculus with Rule-based Algorithmic Model

Abstract

This study aims to develop an automated system for generating derivative function questions to enhance learning and assessment in calculus education. The system uses a rule-based algorithmic approach to generate questions covering various derivative rules, including constant, power, sum, difference, product, quotient, and chain rules, with randomly generated coefficients and exponents. The system's performance was evaluated by measuring the accuracy of the generated questions, achieving a validity rate of 95.63%, and execution time, with an average of 0.00115 milliseconds per question, indicating high efficiency and effectiveness. The results show that the system successfully generates valid questions across various derivative rules, offering significant contributions to both students and educators in the context of calculus education. The system can be further developed by adding additional derivative rules and integrated into larger educational platforms to support a more comprehensive learning experience.