การพัฒนาแบบจำลองการผลิตรายการ เพื่อการศึกษาแบบมีปฏิสัมพันธ์โดยใช้ปัญญาประดิษฐ์สนับสนุน

Apisit Thaoyabut; Sasiyanai Sanpang; Seksan Amatmontree; Kemmanat Mingsiritham; Wachira Brahmawong

Authors

Apisit Thaoyabut Office of Educational Technology, Sukhothai Thammathirat Open University
Sasiyanai Sanpang Office of Educational Technology, Sukhothai Thammathirat Open University
Seksan Amatmontree Office of Educational Technology, Sukhothai Thammathirat Open University
Kemmanat Mingsiritham Office of Educational Technology, Sukhothai Thammathirat Open University
Wachira Brahmawong Office of Educational Technology, Sukhothai Thammathirat Open University

Keywords:

artificial intelligence, interactive video, educational program, production model, educational technology

Abstract

This study aimed to 1) develop an AI-supported interactive educational program production model and 2) evaluate the quality of the AI-supported interactive educational program production model. The study employed a research and development (R&D) design and was carried out in two phases. Phase 1 involved reviewing related documents and research studies and conducting in-depth interviews with experts to analyze problems and needs, synthesize the components of the model, and develop an initial prototype. Phase 2 involved evaluating the quality of the model and the prototype by 25 purposively selected experts. The research instruments included a document and research analysis form, a semi-structured in-depth interview guide, a component synthesis record form, a model quality evaluation form, a prototype quality evaluation form, and explanatory documents for the model and prototype. Data were analyzed using content analysis, mean, and standard deviation.

The findings revealed that: 1) the developed model consisted of five major components: (1) defining input data and learning outcomes, (2) generating prompts and analyzing content with artificial intelligence, (3) creating and managing interactive activities, (4) reviewing and simulating use, and (5) exporting outputs for actual implementation. The in-depth interviews showed that experts recognized the need for tools that reduce the time required for video analysis, support question generation aligned with learning outcomes, and allow instructors to review outputs before actual use. The prototype supported video input from YouTube and MP4 files, input data specification including video links, lesson titles, number of questions, difficulty levels, question types, and learning outcomes connected to video content, prompt generation for artificial intelligence to create questions in JSON format, manual question creation by instructors, interactive video simulation, and output export as a link or iframe for Moodle; and 2) the expert quality evaluation found that the overall quality of the model was at the highest level (M = 4.73, SD = 0.45), and the prototype developed according to the model was also rated at the highest level (M = 4.72, SD = 0.45). Highly rated aspects included the potential to increase the speed of media development, reduce the workload of instructors or media producers, ensure the appropriateness of artificial intelligence use in each step, and support the application of the prototype to actual media development.

References

ยุทธนา โสจันทึก, ศรินย์พร ชัยวิศิษฎ์, และสุกานดา จงเสริมตระกูล. (2568). การพัฒนากิจกรรมการเรียนรู้ตามแนวทางการเล่าเรื่องดิจิทัลด้วยปัญญาประดิษฐ์แบบรู้สร้างเพื่อส่งเสริมการรู้ดิจิทัลสำหรับนักเรียนระดับชั้นประถมศึกษาปีที่ 5. วารสารเทคโนโลยีและสื่อสารการศึกษา คณะศึกษาศาสตร์ มหาวิทยาลัยมหาสารคาม, 8(28), 67–78. https://so02.tci-thaijo.org/index.php/etcedumsujournal/article/view/282221.

ศิรดา เทียนขาว. (2567). การทดลองการใช้เทคนิคการใช้ปัญญาประดิษฐ์เพื่อพัฒนาการเขียนเล่าเรื่องเป็นภาษาอังกฤษ. วารสารวิจัยราชภัฏธนบุรี รับใช้สังคม, 10(2), 82–91. https://so02.tci-thaijo.org/index.php/DRURDI/article/view/273056.

Deng, R., Yang, Y., & Shen, S. (2025). Impact of question presence and interactivity in instructional videos on student learning. Education and Information Technologies, 30, 1635–1663. https://doi.org/10.1007/s10639-024-12984-2.

Mayer, R. E. (2014). Cognitive theory of multimedia learning. In R. E. Mayer (Ed.),

The Cambridge handbook of multimedia learning (2nd ed., pp. 43–71). Cambridge University Press. https://doi.org/10.1017/CBO9781139547369.005.

Mayer, R. E. (2024). The past, present, and future of the cognitive theory of multimedia learning. Educational Psychology Review, 36, Article 8. https://doi.org/ 10.1007/s10648-023-09842-1.

Monib, W. K., Qazi, A., Apong, R. A., Azizan, M. T., De Silva, L., & Yassin, H. (2024). Generative AI and future education: A review, theoretical validation, and authors' perspective on challenges and solutions. PeerJ Computer Science, 10, e2105. https://doi.org/10.7717/peerj-cs.2105.

Noetel, M., Griffith, S., Delaney, O., Sanders, T., Parker, P., del Pozo Cruz, B., & Lonsdale, C. (2021). Video improves learning in higher education: A systematic review. Review of Educational Research, 91(2), 204–236. https://doi.org/10.3102/0034654321990713.

Ogunleye, B., Zakariyyah, K. I., Ajao, O., Olayinka, O., & Sharma, H. (2024). A systematic review of generative AI for teaching and learning practice. Education Sciences, 14(6), 636. https://doi.org/10.3390/educsci14060636.

Twabu, K. (2025). Enhancing the cognitive load theory and multimedia learning framework with AI insight. Discover Education, 4, 160. https://doi.org/10.1007/s44217-025-00592-6.

Xia, Q., Weng, X., Ouyang, F., Lin, T. J., & Chiu, T. K. F. (2024). A scoping review on how generative artificial intelligence transforms assessment in higher education. International Journal of Educational Technology in Higher Education, 21(1), 40. https://doi.org/10.1186/s41239-024-00468-z.