Abstract: Research focuses on evaluating subjective answers, a task demanding significant time and dedication. Introducing a machine learning and natural language processing-driven method for this purpose, the system employs natural language processing combined with a Random Forest model to categorize subjective answers. The approach includes data preprocessing, feature extraction, and classification, aiming to enhance the accuracy and efficiency of evaluating subjective answers. This study not only improves the evaluation process but also contributes to advancing methods in automated assessment. Designed to be adaptable to various educational contexts, the implementation handles diverse types of subjective responses. By automating the evaluation process, educators can save time and allocate more resources to other critical teaching activities. Additionally, the method provides a consistent and unbiased assessment, reducing human error and subjectivity. Research underscores the potential of integrating advanced machine learning techniques into educational tools, paving the way for more innovative applications in the future.

Keywords: Machine Learning, Natural Language Processing, Random Forest, Answer Assessment, Education,

| DOI: 10.17148/IARJSET.2024.11672