Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/11630
Title: Identifying Challenges and Interaction Issues in a Generative AI-Assisted Code Description Activity for Programming Beginners
Authors: Wu, Muyang
Hong, Sumin
Xiao, Ruiwei
Keywords: Learning Sciences
Issue Date: 2025
Publisher: International Society of the Learning Sciences
Citation: Wu, M., Hong, S., & Xiao, R. (2025). Identifying Challenges and Interaction Issues in a Generative Ai-Assisted Code Description Activity for Programming Beginners. 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. 2895-2897). 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 challenges programming beginners face when using Generative AI to describe coding intentions. We analyzed data from 120 students where students described problems, and AI generated code. Performance was evaluated across 48 tasks in eight categories using metrics. Our findings indicate that tasks in the “dictionaries” category are the most challenging for beginners. Additionally, we identified recurring interaction issues such as ambiguous instructions, assumptions about AI understanding, and misalignment with code logic.
Description: Poster
URI: https://doi.org/10.22318/icls2025.505045
https://repository.isls.org//handle/1/11630
Appears in Collections:ISLS Annual Meeting 2025

Files in This Item:
File SizeFormat 
ICLS2025_2895-2897.pdf315.86 kBAdobe PDFView/Open


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