Particle Builder -- Learn about the Standard Model while playing against an AI
Project Overview
The document explores the integration of generative AI in education, highlighting the development of 'Particle Builder Online', a web-based educational game tailored for high school physics students focused on the Standard Model of Particle Physics. By incorporating an AI opponent, the game creates an interactive learning environment that facilitates deeper engagement with complex physics concepts. Initial studies show that students using this game exhibit significant improvements in understanding the subject matter and demonstrate higher levels of engagement compared to traditional instructional methods. Overall, the findings suggest that generative AI applications, like gaming platforms, can enhance educational outcomes by making learning more interactive and effective, particularly in challenging subjects such as physics.
Key Applications
Particle Builder Online
Context: High school physics education, tailored to the International Baccalaureate and the Australian Curriculum.
Implementation: Implemented as a web-based game where students play against an AI opponent or peers, with gameplay mechanics designed to teach particle physics concepts.
Outcomes: Significant improvement in understanding particle physics concepts, higher enjoyment ratings (6.3/7) and learning ratings (5.4/7) compared to traditional lessons.
Challenges: Limited availability of interactive resources for particle physics; potential need for more sophisticated AI in future versions.
Implementation Barriers
Resource Availability
Lack of interactive learning resources for topics like the Standard Model of Particle Physics.
Proposed Solutions: Development of engaging educational tools like Particle Builder to fill this gap.
Project Team
Mohammad Attar
Researcher
Andrew Carse
Researcher
Yeming Chen
Researcher
Thomas Green
Researcher
Jeong-Yeon Ha
Researcher
Yanbai Jin
Researcher
Amy McWilliams
Researcher
Theirry Panggabean
Researcher
Zhengyu Peng
Researcher
Lujin Sun
Researcher
Jing Ru
Researcher
Jiacheng She
Researcher
Jialin Wang
Researcher
Zilun Wei
Researcher
Jiayuan Zhu
Researcher
Lachlan McGinness
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Mohammad Attar, Andrew Carse, Yeming Chen, Thomas Green, Jeong-Yeon Ha, Yanbai Jin, Amy McWilliams, Theirry Panggabean, Zhengyu Peng, Lujin Sun, Jing Ru, Jiacheng She, Jialin Wang, Zilun Wei, Jiayuan Zhu, Lachlan McGinness
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai