Education Sciences, Год журнала: 2024, Номер 14(12), С. 1325 - 1325

Опубликована: Ноя. 30, 2024

In diverse classrooms, one of the challenges educators face is creating assessments that reflect different cultural background every student. this study presents a novel approach to automatic generation and context-specific science items for K-12 education using generative AI (GenAI). We first developed GenAI Culturally Responsive Science Assessment (GenAI-CRSciA) framework connects CRSciA, specifically key tenets such as indigenous language, Indigenous knowledge, ethnicity/race, religion, with capabilities GenAI. Using CRSciA framework, along interactive guided dynamic prompt strategies, was used develop CRSciA-Generator tool within OpenAI platform. The allows users automatically generate assessment item are customized align their students’ contextual needs. conducted pilot demonstration between base GPT-4o (using standard prompts), both tools were tasked generating CRSciAs aligned Next Generation Standard on predator prey relationship students from Ghana, USA, China. results showed output incorporated more tailored context each specific group examples, traditional stories lions antelopes in Native American views wolves Taoist or Buddhist teachings Amur tiger China compared GPT-4o. However, due focus nationality demonstration, treated countries culturally homogeneous, overlooking subcultural diversity these countries. Therefore, we recommend provide detailed information about when CRSciA-Generator. further future studies involving expert reviews assess validity generated by

Язык: Английский