Is ChatGPT Able to Generate Texts that Are Easy to Understand and Read?
摘要
The emergence of generative artificial intelligence applications in recent years has opened up the possibility of automatically generating text tailored to the needs of users. However, is the text generated by these tools easily readable and understandable? This study aims to analyze the ChatGPT's capacity to generate easy to understand texts in Spanish, while adhering to the recommended guidelines for Plain Language. The comprehensiveness of several websites belonging to the Public Administration in Spain has been analyzed. Moreover, ChatGPT was requested to enhance these texts in accordance with the guidelines of Plain Language in Spanish. The original texts and those generated by ChatGPT were then compared to analyze the primary linguistic indicators of different Plain Language guidelines. The study presents a quantitative analysis demonstrating that the new texts generated by ChatGPT do not adhere to Plain Language guidelines. Additionally, the study highlights the use of linguistic elements that should be avoided.