Index modelling assessment tool on level of comprehension complexity

• Main Author: Tang, Glenn Jie Xian
• Other Authors: Lye Sun Woh
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering
• Online Access: https://hdl.handle.net/10356/181739
• Institution: Nanyang Technological University

In a knowledge-driven world like today, comprehension skills are essential for problem solving and to process complex information. A good grasp of comprehension allows for critical thinking, adaptability, and effective decision-making. In the area of education, it ensures learners truly understand the academic material and prepares them for the future. This report presents an assessment tool designed to categorize test questions into different levels of comprehension, aiming to automate the categorization process and to quantify the level of complexity of a set of questions. The tool uses keyword and sentence structure to classify questions into four comprehension levels. It has the ability to support two types of questions: open-ended and multiple-choice. The results are organized into another sheet in the same Excel file, with categories of questions and a calculated Comprehension Index to assist in evaluating the difficulty of the test paper. While the tool is successful in categorizing most of the questions accurately, its performance is limited by a small training dataset and the variation of ways a question can be phrased. The report discusses these limitations and provides recommendations to improve the accuracy of the model. Conclusively, this tool serves as a foundational step toward automating question categorization and improving assessment processes of test papers.