<![CDATA[In the edu-digital era, Learning Management Systems (LMS) have become pivotal in delivering and managing education. However, many LMS platforms lack sophisticated analytical tools to evaluate the quality of post-test assessments. This research explores the application of Item Response Theory (IRT) as a psychometric model integrated into an LMS to enhance post-test analysis. By leveraging IRT, the system can evaluate item difficulty, discrimination, and guessing parameters, providing more accurate insights into both test quality and student ability levels. The study implements a three-parameter logistic (3PL) IRT model and integrates it into an LMS prototype. Empirical data from real student post-tests are analyzed to validate the model's effectiveness. The results demonstrate that IRT-based analysis significantly improves the assessment feedback mechanism, allowing educators to identify poorly performing items, adapt instructional strategies, and personalize learning paths. This research contributes to the development of intelligent assessment systems in educational technology, promoting more effective, fair, and data-driven evaluation processes.]]>
Copyrights © 2025
