IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i15p3400-d1210228.html
   My bibliography  Save this article

Differentiating Chat Generative Pretrained Transformer from Humans: Detecting ChatGPT-Generated Text and Human Text Using Machine Learning

Author

Listed:
  • Iyad Katib

    (Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia)

  • Fatmah Y. Assiri

    (Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia)

  • Hesham A. Abdushkour

    (Nautical Science Department, Faculty of Maritime Studies, King Abdulaziz University, Jeddah 21589, Saudi Arabia)

  • Diaa Hamed

    (Faculty of Earth Sciences, King Abdulaziz University, Jeddah 21589, Saudi Arabia)

  • Mahmoud Ragab

    (Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
    Department of Mathematics, Faculty of Science, Al-Azhar University, Naser City, Cairo 11884, Egypt
    Centre for Artificial Intelligence in Precision Medicines, King Abdulaziz University, Jeddah 21589, Saudi Arabia)

Abstract

Recently, the identification of human text and ChatGPT-generated text has become a hot research topic. The current study presents a Tunicate Swarm Algorithm with Long Short-Term Memory Recurrent Neural Network (TSA-LSTMRNN) model to detect both human as well as ChatGPT-generated text. The purpose of the proposed TSA-LSTMRNN method is to investigate the model’s decision and detect the presence of any particular pattern. In addition to this, the TSA-LSTMRNN technique focuses on designing Term Frequency–Inverse Document Frequency (TF-IDF), word embedding, and count vectorizers for the feature extraction process. For the detection and classification processes, the LSTMRNN model is used. Finally, the TSA is employed for selecting the parameters for the LSTMRNN approach, which enables improved detection performance. The simulation performance of the proposed TSA-LSTMRNN technique was investigated on benchmark databases, and the outcome demonstrated the advantage of the TSA-LSTMRNN system over other recent methods with a maximum accuracy of 93.17% and 93.83% on human- and ChatGPT-generated datasets, respectively.

Suggested Citation

  • Iyad Katib & Fatmah Y. Assiri & Hesham A. Abdushkour & Diaa Hamed & Mahmoud Ragab, 2023. "Differentiating Chat Generative Pretrained Transformer from Humans: Detecting ChatGPT-Generated Text and Human Text Using Machine Learning," Mathematics, MDPI, vol. 11(15), pages 1-19, August.
    • Handle: RePEc:gam:jmathe:v:11:y:2023:i:15:p:3400-:d:1210228
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/15/3400/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/11/15/3400/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:15:p:3400-:d:1210228. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.