{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:36:49Z","timestamp":1784547409176,"version":"3.55.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The rapid advancement of AI, particularly artificial neural networks, has led to revolutionary breakthroughs and applications, such as text-generating tools and chatbots. However, this potent technology also introduces potential misuse and societal implications, including privacy violations, misinformation, and challenges to integrity and originality in academia. Several studies have attempted to distinguish and classify AI-generated textual content from human-authored work, but their performance remains questionable, particularly for AI models utilizing large language models like ChatGPT.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address this issue, we compiled a dataset consisting of both human-written and AI-generated (ChatGPT) content. This dataset was then used to train and evaluate a range of machine learning and deep learning models under various training conditions. We assessed the efficacy of different models in detecting and classifying AI-generated content, with a particular focus on transformer-based architectures.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Experimental results demonstrate that the proposed RoBERTa-based custom deep learning model achieved an F1-score of 0.992 and an accuracy of 0.991, followed by DistilBERT, which yielded an F1-score of 0.988 and an accuracy of 0.988. These results indicate exceptional performance in detecting and classifying AI-generated content.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Our findings establish a robust baseline for the detection and classification of AI-generated textual content. This work marks a significant step toward mitigating the potential misuse of AI-powered text generation tools by providing a reliable approach for distinguishing between human and AI-generated text. Future research could explore the generalizability of these models across different AI-generated content sources and address evolving challenges in AI text detection.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1458707","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:46Z","timestamp":1743767506000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Detection and classification of ChatGPT-generated content using deep transformer models"],"prefix":"10.3389","volume":"8","author":[{"given":"Mahdi","family":"Maktabdar Oghaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakshmi","family":"Babu Saheer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kshipra","family":"Dhame","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gayathri","family":"Singaram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"B1","first-page":"397","article-title":"\u201cArtificial intelligence is a tool for cheating academic integrity,\u201d","author":"Abd-Elaal","year":"2019"},{"key":"B2","doi-asserted-by":"publisher","first-page":"100006","DOI":"10.1016\/j.mlwa.2020.100006","article-title":"Chatbots: history, technology, and applications","volume":"2","author":"Adamopoulou","year":"2020","journal-title":"Mach. Learn. Appl"},{"key":"B3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.52866\/ijcsm.2022.01.01.013","article-title":"Has the future started? the current growth of artificial intelligence, machine learning, and deep learning","volume":"3","author":"Aggarwal","year":"2022","journal-title":"Iraqi J. Comput. Sci. Math"},{"key":"B4","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1145\/3386527.3406723","article-title":"\u201cExaminator: a plagiarism detection tool for take-home exams,\u201d","volume-title":"Proceedings of the Seventh ACM Conference on Learning @ Scale","author":"Apoorv","year":"2020"},{"key":"B5","doi-asserted-by":"publisher","first-page":"118034","DOI":"10.1016\/j.eswa.2022.118034","article-title":"Improving plagiarism detection in text document using hybrid weighted similarity","volume":"207","author":"Arabi","year":"2022","journal-title":"Expert Syst. Appl"},{"key":"B6","first-page":"19","article-title":"\u201cArtificial intelligence marketing: chatbots,\u201d","author":"Arsenijevic","year":"2019"},{"key":"B7","first-page":"421","author":"Beresneva","year":"2016"},{"key":"B8","doi-asserted-by":"publisher","first-page":"53","DOI":"10.5281\/ZENODO.7636568","article-title":"Speculative futures on ChatGPT and generative artificial intelligence (AI): a collective reflection from the educational landscape","volume":"18","author":"Bozkurt","year":"2023","journal-title":"Asian J. Distance Educ."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.07228","article-title":"The malicious use of artificial intelligence: forecasting, prevention, and mitigation","author":"Brundage","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"B11","first-page":"565","author":"Eissen","year":"2006"},{"key":"B12","volume-title":"Encyclopedia of Human Computer Interaction","author":"Ghaoui","year":"2005"},{"key":"B13","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1145\/1066677.1066854","article-title":"\u201cTool support for plagiarism detection in text documents,\u201d","volume-title":"Proceedings of the 2005 ACM Symposium on Applied Computing","author":"Gruner","year":"2005"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90869-4_6","author":"Helbing","year":"2019","journal-title":"Societal, Economic, Ethical and Legal Challenges of the Digital Revolution: from Big Data to Deep Learning, Artificial Intelligence, and Manipulative Technologies"},{"key":"B15","author":"Henderson","year":"2009","journal-title":"Encyclopedia of Computer Science and Technology"},{"key":"B16","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.18653\/v1\/D15-1162","article-title":"\u201cAn improved non-monotonic transition system for dependency parsing,\u201d","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Honnibal","year":"2015"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44041-1_114","article-title":"Generating sentiment-preserving fake online reviews using neural language models and their human-and machine-based detection","author":"Ifeoluwa Adelani","year":"2019","journal-title":"arXiv e-prints arXiv"},{"key":"B18","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1145\/3375627.3375873","article-title":"\u201cMonitoring misuse for accountable \u2018artificial intelligence as a service',\u201d","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","author":"Javadi","year":"2020"},{"key":"B19","unstructured":"Plagiarism detection tools and techniques: a comprehensive survey\n          \n          47\n          64\n          \n            \n              Jiffriya\n              M.\n            \n            \n              Jahan\n              M.\n            \n            \n              Ragel\n              R.\n            \n          \n          J. Sci.-FAS-SEUSL\n          2\n          2021"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2771","DOI":"10.24996\/ijs.2021.62.8.30","article-title":"Plagiarism detection methods and tools: an overview","volume":"62","author":"Khaled","year":"2021","journal-title":"Iraqi J. Sci"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.35542\/osf.io\/fnh48","article-title":"Will chatgpt get you caught? rethinking of plagiarism detection","author":"Khalil","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"B22","doi-asserted-by":"publisher","first-page":"564","DOI":"10.5281\/zenodo.3709267","article-title":"Artificial intelligence and problems of ensuring cyber security","volume":"13","author":"Khisamova","year":"2019","journal-title":"Int. J. Cyber Criminol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"5614","DOI":"10.3390\/su15075614","article-title":"Chatbots in education and research: a critical examination of ethical implications and solutions","volume":"15","author":"Kooli","year":"2023","journal-title":"Sustainability"},{"key":"B24","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/978-3-319-24403-7_8","article-title":"\u201cDetection of computer-generated papers in scientific literature,\u201d","volume-title":"Creativity and Universality in Language","author":"Labb\u00e9","year":"2016"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030","article-title":"Neural architectures for named entity recognition","author":"Lample","year":"2016","journal-title":"CoRR, abs"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1008.0706","article-title":"Algorithmic detection of computer generated text","author":"Lavoie","year":"2010","journal-title":"arXiv preprint arXiv"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"Roberta: a robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"B28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1330598.1330642","article-title":"\u201cComputer-based plagiarism detection methods and tools: an overview,\u201d","volume-title":"Proceedings of the 2007 International Conference on Computer Systems and Technologies","author":"Lukashenko","year":"2007"},{"key":"B29","author":"Morton","year":"1978","journal-title":"Literary Detection: How to Prove Authorship and Fraud in Literature and Documents"},{"key":"B30","first-page":"288","author":"Nguyen-Son","year":"2018"},{"key":"B31","first-page":"1504","author":"Nguyen-Son","year":"2017"},{"key":"B32","first-page":"997","author":"Potthast","year":"2010"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.01108","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"B34","first-page":"08Z","volume":"39","year":"2023","journal-title":"spaCy Lookups Data"},{"key":"B35","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s41060-021-00299-5","article-title":"Detecting computer-generated disinformation","volume":"13","author":"Stiff","year":"2022","journal-title":"Int. J. Data Sci. Anal"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1007\/s11192-018-2789-4","article-title":"Detecting automatically generated sentences with grammatical structure similarity","volume":"116","author":"Tien","year":"2018","journal-title":"Scientometrics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s40561-023-00237-x","article-title":"What if the devil is my guardian angel: chatgpt as a case study of using chatbots in education","volume":"10","author":"Tlili","year":"2023","journal-title":"Smart Learn. Environ"},{"key":"B38","author":"Vasiliev","year":"2020","journal-title":"Natural Language Processing with Python and spaCy: A Practical Introduction."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1458707\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:51:56Z","timestamp":1743767516000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1458707\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,4]]},"references-count":38,"alternative-id":["10.3389\/frai.2025.1458707"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1458707","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,4]]},"article-number":"1458707"}}