Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175595,
        author = {Dr.R.Hamsaveni and Alechelle  Ramya Krishna and B Manoj Kumar raju and S Poojitha},
        title = {Generates Quizzes Based on Topics Using NLP and Predefined Question Banks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3832-3842},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175595},
        abstract = {Artificial Intelligence (AI) and Natural Language Processing (NLP) are driving a transformation in education through the automation of quiz generation. This project employs AI to create quizzes by combining predefined question banks with NLP-based topic extraction techniques. Traditional methods of quiz creation are labor-intensive and time-consuming, while AI-based solutions streamline this process by enhancing efficiency and offering tailored customization. The proposed system uses NLP techniques to extract keywords from educational material, matches these terms to a preexisting question bank, and dynamically generates quizzes. Advanced deep learning models are implemented to optimize question selection, ensuring an appropriate balance of difficulty levels. Additionally, the system adapts to individual users by providing personalized question recommendations based on their performance, fostering a more engaging and interactive learning environment. This project aims to simplify the process of content assessment and enhance personalized learning by integrating machine learning algorithms and AI-driven evaluation. The quizzes generated by the system support various formats, including multiple choice questions (MCQs), fill-in-the-blanks, and short-answer questions. Furthermore, the system includes real-time analytics that monitor user progress and dynamically adjust quiz difficulty based on performance to achieve greater accuracy, the system incorporates techniques such as Named Entity Recognition (NER), Term Frequency Inverse Document Frequency (TF-IDF), and BERT embeddings to refine question generation. A feedback loop is also introduced, enabling continuous model improvements through user interactions and responses.},
        keywords = {},
        month = {April},
        }