International Journal of Scientific Research and Engineering Development

Preparing examination question papers manually is a time-consuming and challenging task for educators. Faculty members must ensure balanced syllabus coverage, appropriate marks distribution, and proper assessment of students across different cognitive levels. Manual preparation often results in inconsistencies, repeated questions, and increased workload. This paper presents BloomQGen, a webbased intelligent question paper generation system that automates the process using Machine Learning techniques and Bloom's Taxonomy. The proposed system preprocesses question datasets, converts textual questions into numerical features using Count Vectorizer, predicts appropriate marks through a Linear Regression model, and categorizes questions according to Bloom's cognitive levels using predefined action verbs. Based on user-defined constraints such as subject, total marks, and Bloom's Taxonomy distribution, the system automatically generates balanced and syllabus-oriented question papers. The application is implemented using the Django framework with Python as the backend and SQLite as the database. The proposed solution reduces manual effort, improves consistency in assessment design, and supports Outcome-Based Education (OBE) by enabling structured and balanced examination paper generation.

Pritesh Premnath Waghmare, A. H Auti, "BloomQGen: An Intelligent Question Paper Generation System Using Machine Learning and Bloom's Taxonomy" International Journal of Scientific Research and Engineering Development, V9(4): Page(533-540) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.