Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images
This study investigates how students utilized artificial intelligence (AI)-generated images to represent their understanding of general relativity concepts. Ten high school students participated in an extracurricular course on relativity theory. Using AI chatbot, these students created visual repres...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
Institute of Physics Publishing
2024
|
| Subjects: | |
| Online Access: | 88881.846299/2023-01 - Coordination for the Improvement of Higher Education Personnel (CAPES) http://hdl.handle.net/20.500.11937/94342 |
| _version_ | 1848765857591721984 |
|---|---|
| author | de Souza, Maira Won, Mihye Treagust, David Serrano, Agostinho |
| author_facet | de Souza, Maira Won, Mihye Treagust, David Serrano, Agostinho |
| author_sort | de Souza, Maira |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This study investigates how students utilized artificial intelligence (AI)-generated images to represent their understanding of general relativity concepts. Ten high school students participated in an extracurricular course on relativity theory. Using AI chatbot, these students created visual representations of 'relativity' before and after the course. The produced images, the accompanying prompts, student interviews, and their test scores were analysed to examine students' conceptual understanding and interactions with AI. Students with a clearer understanding of relativity tended to focus their prompts on more central concepts like spacetime deformation. In contrast, those with a weaker understanding leaned towards more tangential ideas. The clarity of their prompts was directly linked to more effective AI interactions, leading to more meaningful image generation. Despite this, some students faced challenges in crafting coherent prompts, resulting in less relevant images, indicating that understanding the concept does not always translate into successful AI engagement. The study underscores the potential of AI-generated images as a tool to illuminate student conceptualisation and interaction skills with AI in the context of complex physics concepts, offering a novel approach to evaluating understanding in advanced scientific topics. |
| first_indexed | 2025-11-14T11:41:55Z |
| format | Journal Article |
| id | curtin-20.500.11937-94342 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T11:41:55Z |
| publishDate | 2024 |
| publisher | Institute of Physics Publishing |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-943422024-04-04T05:22:55Z Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images de Souza, Maira Won, Mihye Treagust, David Serrano, Agostinho artifical intelligence relativity visualization This study investigates how students utilized artificial intelligence (AI)-generated images to represent their understanding of general relativity concepts. Ten high school students participated in an extracurricular course on relativity theory. Using AI chatbot, these students created visual representations of 'relativity' before and after the course. The produced images, the accompanying prompts, student interviews, and their test scores were analysed to examine students' conceptual understanding and interactions with AI. Students with a clearer understanding of relativity tended to focus their prompts on more central concepts like spacetime deformation. In contrast, those with a weaker understanding leaned towards more tangential ideas. The clarity of their prompts was directly linked to more effective AI interactions, leading to more meaningful image generation. Despite this, some students faced challenges in crafting coherent prompts, resulting in less relevant images, indicating that understanding the concept does not always translate into successful AI engagement. The study underscores the potential of AI-generated images as a tool to illuminate student conceptualisation and interaction skills with AI in the context of complex physics concepts, offering a novel approach to evaluating understanding in advanced scientific topics. 2024 Journal Article http://hdl.handle.net/20.500.11937/94342 10.1088/1361-6552/ad1e71 English 88881.846299/2023-01 - Coordination for the Improvement of Higher Education Personnel (CAPES) http://creativecommons.org/licenses/by/4.0/ Institute of Physics Publishing fulltext |
| spellingShingle | artifical intelligence relativity visualization de Souza, Maira Won, Mihye Treagust, David Serrano, Agostinho Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title | Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title_full | Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title_fullStr | Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title_full_unstemmed | Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title_short | Visualising relativity: assessing high school students' understanding of complex physics concepts through AI-generated images |
| title_sort | visualising relativity: assessing high school students' understanding of complex physics concepts through ai-generated images |
| topic | artifical intelligence relativity visualization |
| url | 88881.846299/2023-01 - Coordination for the Improvement of Higher Education Personnel (CAPES) http://hdl.handle.net/20.500.11937/94342 |