https://ph05.tci-thaijo.org/index.php/JIIST <p class="ng-star-inserted"><span class="ng-star-inserted">The <strong>Journal of Intelligent Informatics and Smart Technology (JIIST) (ISSN: 2586-9167)</strong> operates under the association of <strong>the</strong> <strong>Artificial Intelligence Association of Thailand (AIAT) and </strong><strong>the IEEE SMC Thailand Chapter</strong><strong>.</strong> It aims to be a publisher of a wide range of high-quality academic journals.</span></p> <p class="ng-star-inserted"><span class="ng-star-inserted">The journal welcomes original articles, review articles, short communications, and case reports in the field of artificial intelligence. This includes topics such as Natural Language Processing, Speech Recognition, Machine Learning, Image Processing, Robotics, Semantic Web, Intelligent Computer-Aided Instruction (ICAI), and Expert Systems, among other related fields. All articles are published in English.</span></p> Artificial Intelligence Association of Thailand en-US Journal of Intelligent Informatics and Smart Technology 2586-9167 https://ph05.tci-thaijo.org/index.php/JIIST/article/view/176 <p><span class="ng-star-inserted">Programming education is becoming more essential due to the increasing demands on coding skills and computer literacy. Consequently, many professional schools and universities are providing programming courses to train future programming engineers. However, making quizzes and practice questions for diverse programming topics can be time-consuming for the teachers, reducing the time they can spend on teaching, such as guiding students and providing personalized feedback. In this paper, we propose an AI-driven question generation using ChatGPT to support Python programming education. We developed an automated program that can generate three types of questions to cover basic programming concepts: </span><span class="ng-star-inserted">Code Understanding Questions</span><span class="ng-star-inserted">, </span><span class="ng-star-inserted">Output Prediction Questions</span><span class="ng-star-inserted">, and </span><span class="ng-star-inserted">Code Completion Questions</span><span class="ng-star-inserted"> by using ChatGPT's language model (LM). For evaluations, we have prepared 28 python source codes and applied 140 generated questions to our </span><span class="ng-star-inserted">Language Understanding</span><span class="ng-star-inserted"> lab members in online setting. The examination was conducted as an unsupervised, open-book assessment, allowing participants to reference materials while answering the questions. This setup aimed to simulate a realistic self-learning environment, reflecting how students typically engage with AI-generated questions outside of formal classroom settings. The application results confirm the validity of the proposal and our initial findings indicate that AI-generated questions are effective in supporting both educators and students for Python programming education.</span></p> Khaing Hsu Wai Ye Kyaw Thu Thazin Myint Oo Nobuo Funabiki Lu Xiqin Akihiro Yamamura Copyright (c) 2025 Journal of Intelligent Informatics and Smart Technology 2025-10-31 2025-10-31 1 7