Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11316
Title: Adaptive Scaffolding with Generative AI Chatbot for Solving Ill-Structured Problems
Authors: Jang, Hyeji
So, Hyo-Jeong
Keywords: Learning Sciences
Issue Date: 2025
Publisher: International Society of the Learning Sciences
Citation: Jang, H. & So, H. (2025). Adaptive Scaffolding With Generative Ai Chatbot for Solving Ill-Structured Problems. In Rajala, A., Cortez, A., Hofmann, R., Jornet, A., Lotz-Sisitka, H., & Markauskaite, L. (Eds.), Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025 (pp. 1555-1559). International Society of the Learning Sciences.
Series/Report no.: Proceedings of the 19th International Conference of the Learning Sciences - ICLS 2025
Abstract: This study investigates the role of generative AI (GenAI) chatbots in supporting students’ ill-structured problem-solving. A GenAI chatbot, Probot, was developed to offer adaptive scaffolding through question prompts during problem representation, solution generation and selection, justification, and monitoring and evaluation. Sixty-one undergraduate students in Korea were divided into control and experimental groups. The experimental group solved an ill-structured problem with Probot while the control group used a non-adaptive chatbot. Interaction patterns with GenAI chatbots were analyzed using Epistemic Network Analysis. Results showed the experimental group had strong connections with orientation in problem analysis, solution analysis, and solution elaboration, suggesting that Probot supported students’ analytical and elaborative thinking. The control group showed strong connections between problem analysis, solution analysis, and solution suggestions, indicating a focus on information and idea-seeking. The findings highlight Probot’s potential in guiding ill-structured problem-solving and offer design insights for adaptive scaffolding.
Description: Short Paper
URI: https://doi.org/10.22318/icls2025.194070
https://repository.isls.org//handle/1/11316
Appears in Collections:ISLS Annual Meeting 2025

Files in This Item:
File SizeFormat 
ICLS2025_1555-1559.pdf338.03 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.