Search and Filter

Repository Feedback

Your feedback helps us improve the repository's content relevance and usability. Please share your thoughts to help us better serve researchers and practitioners.

Submit feedback

Submit a research study

Contribute to the repository:

Add a paper

Personalized Parsons Puzzles as Scaffolding Enhance Practice Engagement Over Just Showing LLM-Powered Solutions

Xinying Hou, University of Michigan
Zihan Wu, University of Michigan
Xu Wang, University of Michigan
Barbara Jane Ericson, University of Michigan
Date
Publisher
arXiv
Link
http://arxiv.org/pdf/2501.09210v1
As generative AI products could generate code and assist students with programming learning seamlessly, integrating AI into programming education contexts has driven much attention. However, one emerging concern is that students might get answers without learning from the LLM-generated content. In this work, we deployed the LLM-powered personalized Parsons puzzles as scaffolding to write-code practice in a Python learning classroom (PC condition) and conducted an 80-minute randomized between-subjects study. Both conditions received the same practice problems. The only difference was that when requesting help, the control condition showed students a complete solution (CC condition), simulating the most traditional LLM output. Results indicated that students who received personalized Parsons puzzles as scaffolding engaged in practicing significantly longer than those who received complete solutions when struggling.
Study at a glance
  • Question: Do interactive AI-generated puzzles engage programming students better than simply showing complete solutions when requesting help?
  • Setting and data: Students in a Python learning classroom during an 80-minute session.
  • Method: Randomized controlled trial (randomized between-subjects study).
Why it matters

As generative AI is integrated into programming education, an emerging concern is that students might get answers without learning from the AI-generated content.

Key findings
  • In a Python classroom, struggling students practiced significantly longer when supported with personalized code-arranging puzzles instead of complete AI solutions.
  • Providing complete AI-generated solutions to struggling students led to significantly less practice time than interactive puzzle-based assistance.
  • Generative AI tools can generate code and deliver personalized puzzle supports to assist students during programming practice.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

What is the application?
Learning – Student Support
Who is the user?
Student
Who age?
Post-Secondary
Why use AI?
Outcomes – Other Academic,
Outcomes – Differentiation
Study design
Impact – Randomized Controlled Trial
Download PDF