Creating and evaluating instructional materials with generative artificial intelligence: visual representations in astronomy education DOI Creative Commons
Hasan Zühtü Okulu

Education and Information Technologies, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Abstract Recent advancements in generative artificial intelligence for visualization offer significant opportunities to develop instructional materials. These can benefit astronomy education, which frequently relies on visual aids like representations. This document analysis study investigates ChatGPT-4o’s capabilities creating and evaluating representations education. Initially, ChatGPT-4o was utilized create illustrating the phases of Moon. visuals were then evaluated based predefined criteria, focusing iconic features reading interpreting representation. Subsequently, existing same topic provided ChatGPT-4o, it asked evaluate these using criteria. Finally, assessments compared with evaluations. Findings suggest that while ChatGPT-4o-generated often contain inaccuracies are potentially misleading students, effectively evaluates read interpret underscores potential utility as a critical tool ensuring quality science It is recommended integrate advanced tools into evaluation processes

Language: Английский

Creating and evaluating instructional materials with generative artificial intelligence: visual representations in astronomy education DOI Creative Commons
Hasan Zühtü Okulu

Education and Information Technologies, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Abstract Recent advancements in generative artificial intelligence for visualization offer significant opportunities to develop instructional materials. These can benefit astronomy education, which frequently relies on visual aids like representations. This document analysis study investigates ChatGPT-4o’s capabilities creating and evaluating representations education. Initially, ChatGPT-4o was utilized create illustrating the phases of Moon. visuals were then evaluated based predefined criteria, focusing iconic features reading interpreting representation. Subsequently, existing same topic provided ChatGPT-4o, it asked evaluate these using criteria. Finally, assessments compared with evaluations. Findings suggest that while ChatGPT-4o-generated often contain inaccuracies are potentially misleading students, effectively evaluates read interpret underscores potential utility as a critical tool ensuring quality science It is recommended integrate advanced tools into evaluation processes

Language: Английский

Citations

0