IJIET 2026 Vol.16(7): 1733-1744
doi: 10.18178/ijiet.2026.16.7.2637
doi: 10.18178/ijiet.2026.16.7.2637
An Intelligent Conversational Agent Based on Adaptive Learning to Enhance Learning Design Competencies of Pre-service Teachers
Sakchai Chaiyarak, Alongkorn Koednet, Anucha Khaengkhan, and Panpachara Pinchinda *
Faculty of Education, Suan Dusit University, Bangkok, Thailand
Email: sakchai_cha@dusit.ac.th (S.C.); alongkorn_koe@dusit.ac.th (A.Ko.); anucha_kha@dusit.ac.th (A.Kh.); panpachara_pin@dusit.ac.th (P.P.)
*Corresponding author
Email: sakchai_cha@dusit.ac.th (S.C.); alongkorn_koe@dusit.ac.th (A.Ko.); anucha_kha@dusit.ac.th (A.Kh.); panpachara_pin@dusit.ac.th (P.P.)
*Corresponding author
Manuscript received December 24, 2025; revised January 9, 2026; accepted February 6, 2026; published July 13, 2026
Abstract—This study aimed to (1) develop an intelligent conversational agent informed by adaptive learning principles; and (2) assess the impact of the agent’s utilisation on the improvement of instructional design skills. A Research and Development (R&D) approach was employed. The participants consisted of 50 third-year undergraduates from the Bachelor of Education program at Suan Dusit University, chosen via cluster sampling. The research instruments included an intelligent conversational agent developed using a LINE Chatbot integrated with generative Artificial Intelligence (AI) technology (EdCafe AI), an instrument quality evaluation form, a knowledge test and instructional design skills assessment, and a satisfaction questionnaire. Data were analysed using descriptive statistics and a dependent t-test, and instrument reliability was examined using Cronbach’s alpha. The results indicated that the developed system comprised two main components: a front-end interface using the LINE Chatbot “LUWIGA” to facilitate learner access and a back-end processing system on the EdCafe AI platform supporting adaptive learning through natural language processing, automated feedback, document and image analysis, and instructional design support. Learning content was additionally linked through the Canva platform to ensure alignment with learning objectives. Expert evaluation showed that the overall quality of the tool was at its highest level. Students’ post-test knowledge achievement was significantly higher than their pre-test scores at the 0.01 level, instructional design skills were rated at a high level, and learner satisfaction was at the highest level. These findings suggest that integrating AI chatbots with adaptive learning principles can effectively support personalised learning and instructional design development.
Keywords—artificial intelligence in education, intelligent conversational agent, adaptive learning, learning design, pre-service teacher
Copyright © 2026 by the authors. This 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 (CC BY 4.0).
Keywords—artificial intelligence in education, intelligent conversational agent, adaptive learning, learning design, pre-service teacher
Cite: Sakchai Chaiyarak, Alongkorn Koednet, Anucha Khaengkhan, and Panpachara Pinchinda, "An Intelligent Conversational Agent Based on Adaptive Learning to Enhance Learning Design Competencies of Pre-service Teachers," International Journal of Information and Education Technology, vol. 16, no. 7, pp. 1733-1744, 2026.
Copyright © 2026 by the authors. This 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 (CC BY 4.0).