Usability Analysis of Text Generation by ChatGPT OpenAI Using System Usability Scale Method
Angelina Patience Mulia, Pirelli Rahelya Piri, Cuk Tho
Abstract
The development of artificial intelligence systems has resulted in various AI products including ChatGPT, which is a new product classified as a chatbot. This research aims to ensure that text generation systems such as ChatGPT open AI have the best level of quality and usability and are able to provide a satisfying experience for users. To measure and evaluate the effectiveness, efficiency and user satisfaction of the ChatGPT platform, researchers used the System Usability Scale (SUS) method. This data collection was carried out using an online questionnaire. After the collected data has been tested for validity and reliability, the researchers then analyzed the data results. From the results of the research conducted, the SUS value of the ChatGPT platform is 67.44. This score is included in the marginal high category of class D, with a reasonable or sufficient interpretation. With the results of the analysis per question item, it shows that users tend to agree that the system runs quite effectively, efficiently, well and is easy to understand. Although ChatGPT is able to perform tasks or commands well. However, it should be noted that not all information loaded by ChatGPT is presented in a complete, current and correct manner. This is because the information presented by ChatGPT is only limited to 2021. Because ChatGPT is a new technology and is still under development, further researchers are expected to test other features or ChatGPT to ensure the stability and reliability of the entire ChatGPT system using other research methods.