Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Designing Child-Centric AI Learning Environments: Insights from LLM-Enhanced Creative Project-Based Learning

Siyu Zha, Yuehan Qiao, Qingyu Hu, Zhongsheng Li, Jiangtao Gong, Yingqing Xu

TL;DR

This study investigates how large language models (LLMs) can augment child-centered, creative project-based learning (PBL) in middle school. Through an exploratory study and a mixed-method instructional experiment, it identifies five design considerations to effectively integrate LLMs into PBL, then demonstrates a four-stage, design-thinking–based program (Discover, Define, Develop, Deliver) augmented by Six Thinking Hats and two LLM tools. Findings show LLMs can enhance information retrieval, problem definition, idea generation, and prototyping, while revealing ambivalent attitudes and implementation challenges related to prompting, mentorship, and collaboration. The work offers design guidelines for structured LLM integration, thinking-tool coupling, mentor training, and collaboration protocols, aiming to scale AI-assisted, child-centered creativity in education.

Abstract

Project-based learning (PBL) is an instructional method that is very helpful in nurturing students' creativity, but it requires significant time and energy from both students and teachers. Large language models (LLMs) have been proven to assist in creative tasks, yet much controversy exists regarding their role in fostering creativity. This paper explores the potential of LLMs in PBL settings, with a special focus on fostering creativity. We began with an exploratory study involving 12 middle school students and identified five design considerations for LLM applications in PBL. Building on this, we developed an LLM-empowered, 48-hour PBL program and conducted an instructional experiment with 31 middle school students. Our results indicated that LLMs can enhance every stage of PBL. Additionally, we also discovered ambivalent perspectives among students and mentors toward LLM usage. Furthermore, we explored the challenge and design implications of integrating LLMs into PBL and reflected on the program. By bridging AI advancements into educational practice, our work aims to inspire further discourse and investigation into harnessing AI's potential in child-centric educational settings.

Designing Child-Centric AI Learning Environments: Insights from LLM-Enhanced Creative Project-Based Learning

TL;DR

This study investigates how large language models (LLMs) can augment child-centered, creative project-based learning (PBL) in middle school. Through an exploratory study and a mixed-method instructional experiment, it identifies five design considerations to effectively integrate LLMs into PBL, then demonstrates a four-stage, design-thinking–based program (Discover, Define, Develop, Deliver) augmented by Six Thinking Hats and two LLM tools. Findings show LLMs can enhance information retrieval, problem definition, idea generation, and prototyping, while revealing ambivalent attitudes and implementation challenges related to prompting, mentorship, and collaboration. The work offers design guidelines for structured LLM integration, thinking-tool coupling, mentor training, and collaboration protocols, aiming to scale AI-assisted, child-centered creativity in education.

Abstract

Project-based learning (PBL) is an instructional method that is very helpful in nurturing students' creativity, but it requires significant time and energy from both students and teachers. Large language models (LLMs) have been proven to assist in creative tasks, yet much controversy exists regarding their role in fostering creativity. This paper explores the potential of LLMs in PBL settings, with a special focus on fostering creativity. We began with an exploratory study involving 12 middle school students and identified five design considerations for LLM applications in PBL. Building on this, we developed an LLM-empowered, 48-hour PBL program and conducted an instructional experiment with 31 middle school students. Our results indicated that LLMs can enhance every stage of PBL. Additionally, we also discovered ambivalent perspectives among students and mentors toward LLM usage. Furthermore, we explored the challenge and design implications of integrating LLMs into PBL and reflected on the program. By bridging AI advancements into educational practice, our work aims to inspire further discourse and investigation into harnessing AI's potential in child-centric educational settings.
Paper Structure (63 sections, 9 figures, 3 tables)

This paper contains 63 sections, 9 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Project-Based Learning in the Classroom
  4. Creative Support Tools in Learning
  5. Large Language Models in Education
  6. Design LLM-empowered PBL Program
  7. Design Considerations from an Exploratory Study
  8. Lack of Clear Steps to Integrate LLMs
  9. Unclear Purpose for LLMs Usage
  10. Fail to formulate prompts to LLMs
  11. Overintervention and Insufficient Guidance from Mentors in LLMs Use.
  12. Challenges in Balancing LLMs Use and Group Collaboration
  13. Experimental Study
  14. Program Design
  15. PBL Process Design: Streamlining PBL for Creative Problem-Solving (Consideration 1)
  16. ...and 48 more sections

Figures (9)

  • Figure 1: Six thinking hats in the PBL design process for LLMs usage
  • Figure 2: Final demo example of the G3 and G4 in the PBL program
  • Figure 3: Students are collaborating with LLMs on their project
  • Figure 4: Thematic analysis map of LLMs boosting various stages of PBL
  • Figure 5: Thematic analysis map of ambivalent perspectives on LLMs in creativity
  • ...and 4 more figures