EVALUATION OF READABILITY INDICES OF CHATGPT-4 AND GOOGLE GEMINI ABOUT MUSHROOM POISONING

Read full text Summarise with VIRAT
Authors: Ökkeş Zortuk, Cihan Bedel
Cited by: 0
References: 31

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Aim: Mushroom poisoning is a significant public health concern. artificial intelligence (AI) technologies have shown remarkable success in mushroom classification and poisoning prevention, challenges remain. It is clear that the complexity and computational demands of deep learning models can act as a barrier for interdisciplinary researchers [10]. In this study, we wanted to compare the readability indices of AI programs in mushroom poisoning cases in the literature. Materials and Methods: This study included 100 questions about mushroom poisoning Questions were compiled from publicly available question-and-answer platforms such as the Quaro program and ChatGPT-5 and Gemini-2.5 Pro AI models compared. Before generating the questions, we instructed both AI models to formulate their responses in language appropriate for a general audience with no prior medical knowledge on the topic. The responses generated by the models were recorded. Results: Gemini's content showed a significantly higher Automated Readability Index (ARI) of 9.89 ± 0.9 compared to Open AI's 8.93 ± 0.78, with a p-value of

Fields of Study & Subjects

Text Readability and Simplification Artificial Intelligence in Healthcare and Education Health Literacy and Information Accessibility

Publication details

Journal / source
Ġylym men densaulyķ saķtau.
Issue
1(28)
Pages
99–105
Publication date
27 February 2026
Language
RU