The Ability of ChatGPT in Paraphrasing Texts and Reducing Plagiarism: A Descriptive Analysis
Authors:
- Soheil HassanipourSHSoheil Hassanipour
- Sandeep NayakSNSandeep Nayak
- Ali BozorgiABAli Bozorgi
- Mohammad-Hossein KeivanlouMKMohammad-Hossein Keivanlou
- Tirth DaveTDTirth Dave
- Abdulhadi AlotaibiAAAbdulhadi Alotaibi
- Farahnaz JoukarFJFarahnaz Joukar
- Parinaz MellatdoustPMParinaz Mellatdoust
- Arash BakhshiABArash Bakhshi
- Dona KuriyakoseDKDona Kuriyakose
- Lakshmi D PolisettyLPLakshmi D Polisetty
- Mallika ChimpiriMCMallika Chimpiri
Open Access
- 8 July 2024
- journal article
- research article
- Published by JMIR Publications Inc. in JMIR Medical Education
- Vol. 10, e53308
Abstract
Background: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out. Objective: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot. Methods: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated. Results: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference −0.51, 95% CI −0.54 to −0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference −0.06, 95% CI −0.08 to −0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001). Conclusion: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work.Keywords
This publication has 22 references indexed in Scilit:
- ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerationsFrontiers in Artificial Intelligence, 2023
- ChatGPT and the Future of Medical WritingRadiology, 2023
- Artificial Intelligence-Enabled Science PoetryACS Energy Letters, 2022
- Plagiarism detection and prevention: a primer for researchersRheumatology, 2021
- Introduction to AI ChatbotsInternational Journal of Engineering Research & Technology, 2020
- PlagiarismIndian Journal of Pathology and Microbiology, 2020
- Not all plagiarism requires a retractionNature, 2014
- Plagiarism in researchMedicine, Health Care and Philosophy, 2014
- Scientific retractions and corrections related to misconduct findingsJournal of Medical Ethics, 2012
- International perspectives on plagiarism and considerations for teaching international traineesUrologic Oncology: Seminars and Original Investigations, 2011