• Journal of Internet of Things and Convergence
• /
• v.10 no.6
• /
• pp.105-110
• /
• 2024

Quizzes in the classroom can enhance students' academic achievement by assessing their understanding of the material. However, instructors often hesitate to actively utilize quizzes because of the additional workload required for creating, grading, and analyzing quiz results. With the recent advancements in Large Language Model (LLM) technology and the widespread use of online survey platforms such as Google Forms, a more efficient environment for leveraging quizzes in classes is now available. This paper proposes a system that utilizes ChatGPT, a representative LLM, to automatically generate quiz questions, conduct quiz exams via Google Forms, and provide grading and feedback. Specifically, the paper discusses the system's requirements and design, along with a prototype implementation. The prototype system was developed in a Python environment, employing the ChatGPT API for quiz question generation and the Google Forms API for administering and grading quizzes. Additionally, the system enables instructors to review and select questions generated by ChatGPT, while quiz questions and students' responses are stored in a database to facilitate both collective and individual learning outcome analysis. The automated quiz generation system offers the advantage of automating the processes of quiz question creation, examination, evaluation, and analysis, significantly alleviating instructors' workload and improving students' academic performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1187-1194
• /
• 2020

We presented a method of deep quiz cropping for automatic construction of quiz pool in online quiz systems. The method detects question boxes and sunda boxes in images captured from test papers by a deep learning-based object detector, and makes pairs of question box and sunda box by the box coupling. We applied the deep quiz cropping to images captured from test papers and achieved successful results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.3
• /
• pp.547-553
• /
• 2009

Moodle is a web-based open-source LMS. This system provides the effective functions for making a various types of quizzes easily. Any interface for making a Cloze-type quiz conveniently, however, are not provided in the Moodle. In this paper, a web-based program has been developed which helps users make the Cloze-type quizzes easily. The program provides a convenient interface and achieved the considerable reduction in time-cost of making the Cloze-type quiz. The program is very helpful for users to try to make a variety of quizzes by using the Cloze-type.