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

Iyad Katib (), Fatmah Y. Assiri, Hesham A. Abdushkour, Diaa Hamed and Mahmoud Ragab
Additional contact information
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

Mathematics, 2023, vol. 11, issue 15, 1-19

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.

Keywords: ChatGPT; artificial intelligence; feature extraction; human-generated text; tunicate swarm algorithm (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/15/3400/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/15/3400/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:15:p:3400-:d:1210228

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().