Text Origin Detection: Unmasking the Source – AI vs Human

ChatGpt is a conversational artificial intelligence that is a member of the generative pre-trained tranformer of the large language model family. The paper examines the challenges associated with discerning between text generated by ChatGPT, an artificial intelligence model, and naturally written human text. Despite the impressive capabilities of ChatGPT, there is a growing concern about the potential misuse of AI -generated content. The primary objective of this research is to address the critical need for a reliable method to differentiate between ChatGPT-generated text and human-authored text. Our study employs a robust machine learning-based approach for text classification, leveraging a diverse dataset and state-of-the-art classifiers. We meticulously explore the nuanced distinctions that exist between automated content, specifically that gen-erated by ChatGPT, and human-generated text. The culmination of our research involves the development and evaluation of an ensemble model, achieving a noteworthy accuracy rate of 80.29 %. This work contributes significantly to the ongoing discourse on the responsible use of AI -generated content.