Open Access Open Access  Restricted Access Subscription Access

AI Based Automated MCQ Generator

Dr. Anitha S, Balasurya G, Dinu Vishruth N V, Jenish C, Kathiresh A

Abstract


This project aims to develop an AI-based Automated MCQ Generator that can dynamically generate multiple-choice questions from user-provided input such as text topics or uploaded study materials. The development of an AI-powered Automated MCQ Generator capable of dynamically creating multiple-choice questions based on user inputs, including uploaded study materials (PDF, DOCX, TXT files) or manually entered topics. Unlike traditional systems that depend on a pre-existing question database, our solution leverages the Gemini API to generate fresh, contextually relevant questions in real time.The system is built with a lightweight and interactive frontend (HTML, CSS, JavaScript) and a Flask-based backend that handles file processing, topic input, and API integration. All MCQs are generated on demand, eliminating the need for static storage. In-memory session management ensures efficient handling of quiz sessions, without reliance on external databases.By automating the MCQ creation process, the project significantly reduces the manual effort required by educators and offers a scalable solution for personalized and adaptive assessments. This tool is especially suited for online education platforms, teachers, and learners seeking quick, intelligent quiz generation tailored to specific learning materials or topics.

 


Full Text:

PDF

References


Mannem Prashanth, Rashmi Prasad, and Aravind Joshi. (2010). Question generation from paragraphs at UPenn: QGSTEC system description. In Proceedings of QG2010: The Third Workshop on Question Generation, pages 84–91.

Colleen E Crangle and Joyce Brothers Kart. (2015). A questions-based investigation of consumer mental Health information. PeerJ, 3:e867.

Gall MD. (1970). The use of questions in teaching. Review of Educational Research, 40: 707 720.

Swart (2010). Evaluation of Final Examination Papers in Engineering: A Case Study Using Bloom’s Taxonomy. IEEE Transactions on Education, (May 2010) Vol. 53, No.2 257-264.

Aldabe, I., De Lacalle, M. L., Maritxalar, M., Martinez, E., and Uria, L. (2006). Arikiturri: an Automatic question generator based on corpora and nlp techniques. In International Conference on Intelligent Tutoring Systems (pp. 584-594). Springer, Berlin, Heidelberg. International Journal on Natural Language Computing (IJNLC) Vol.10, No.2, April 2021

Folajimi, Y. O., and Omojola, O. E. (2013). Natural language processing techniques for automatic test Questions generation using discourse connectives. Journal of Computer Science and Its Application, 20(2), 6076.

Aditya S. (2018). Using Natural Language Processing for Smart Question Generation. An Intel Developer Program Documentation. https://software.intel.com/en-us/articles/using- natural language processing forsmart-question-generation.

Susanti, Y., Tokunaga, T., Nishikawa, H., and Obari, H. 2018. Automatic distractor generation for multiple Choice English vocabulary questions. Research and Practice in Technology Enhanced Learning, 13(1), 15.

Das, B., and Majumder, M. (2017). Factual open cloze question generation for assessment of learne’s knowledge. International Journal of Educational Technology in Higher Education, 14(1),24.


Refbacks

  • There are currently no refbacks.