| Autor: |
Gatti Junior, Wilian, Marasco, Emily, Kim, Beaumie, Behjat, Laleh, Eggermont, Marjan |
| Předmět: |
|
| Zdroj: |
International Journal of Serious Games; Dec2023, Vol. 10 Issue 4, p33-54, 22p |
| Abstrakt: |
This study explores the application of Large Language Models (LLMs), such as ChatGPT, in designing educational board games, and be deployed as objects-to-think-with It aims to guide educators through three pivotal design phases: ideation, where ChatGPT suggests themes and mechanisms aligned with learning goals; customization, providing templates for tailored games; and feedback on prototypes to enhance game components and mechanisms. We also compared the use of ChatGPT in a game ideation process, contrasting with a traditional game design approach. Although offering a dynamic platform blending computational prowess and creativity, ChatGPT and similar LLMs pose challenges. They can exhibit biases from training datasets, affecting game inclusivity. They may also generate inaccurate details, propose counter-intuitive rules, and misinterpret feedback, resulting in unintended dynamics. Addressing these challenges necessitates a designer critical evaluation of LLM suggestions and the infusion of human creativity and intuition. This research advances discussions on AI in education by highlighting both the potential and the challenges of employing such innovative tools in developing serious games, aiming to foster a balanced and informed approach to integrating LLMs in educational game design. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
