{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T11:50:45Z","timestamp":1782301845688,"version":"3.54.5"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"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:p>Generative AI models, including ChatGPT, Gemini, and Claude, are increasingly significant in enhancing K\u201312 education, offering support across various disciplines. These models provide sample answers for humanities prompts, solve mathematical equations, and brainstorm novel ideas. Despite their educational value, ethical concerns have emerged regarding their potential to mislead students into copying answers directly from AI when completing assignments, assessments, or research papers. Current detectors, such as GPT-Zero, struggle to identify modified AI-generated texts and show reduced reliability for English as a Second Language learners. This study investigates detection of academic cheating by use of generative AI in high-stakes writing assessments. Classical machine learning models, including logistic regression, XGBoost, and support vector machine, are used to distinguish between AI-generated and student-written essays. Additionally, large language models including BERT, RoBERTa, and Electra are examined and compared to traditional machine learning models. The analysis focuses on prompt 1 from the ASAP Kaggle competition. To evaluate the effectiveness of various detection methods and generative AI models, we include ChatGPT, Claude, and Gemini in their base, pro, and latest versions. Furthermore, we examine the impact of paraphrasing tools such as GPT-Humanizer and QuillBot and introduce a new method of using synonym information to detect humanized AI texts. Additionally, the relationship between dataset size and model performance is explored to inform data collection in future research.<\/jats:p>","DOI":"10.3389\/frai.2024.1469197","type":"journal-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T06:19:24Z","timestamp":1731997164000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Investigating generative AI models and detection techniques: impacts of tokenization and dataset size on identification of AI-generated text"],"prefix":"10.3389","volume":"7","author":[{"given":"Haowei","family":"Hua","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Co-Jiayu","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"182","DOI":"10.4018\/979-8-3693-1351-0.ch009","article-title":"\u201cArtificial intelligence (AI) and cheating: the concept of generative artificial intelligence (GenAI),\u201d","volume-title":"Transforming Education With Generative AI: Prompt Engineering and Synthetic Content Creation","author":"Akka\u015f","year":"2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"25","DOI":"10.56297\/BUKA4060\/XHLD5365","article-title":"Who wrote this essay? Detecting AI-generated writing in second language education in higher education","volume":"23","author":"Alexander","year":"2023","journal-title":"Teach. English Technol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1080\/03007995.2024.2310086","article-title":"Between human and AI: assessing the reliability of ai text detection tools","volume":"40","author":"Bellini","year":"2024","journal-title":"Curr. Med. Res. Opin"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2","DOI":"10.37074\/jalt.2023.6.2.12","article-title":"Detecting ai content in responses generated by chatgpt, youchat, and chatsonic: the case of five AI content detection tools","volume":"6","author":"Chaka","year":"2023","journal-title":"J. Appl. Learn. Teach"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.37074\/jalt.2024.7.1.33","article-title":"Accuracy pecking order-how 30 AI detectors stack up in detecting generative artificial intelligence content in university English L1 and English L2 student essays","volume":"7","author":"Chaka","year":"2024","journal-title":"J. Appl. Learn. Teach"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.04736","article-title":"On the possibilities of AI-generated text detection","author":"Chakraborty","year":"2023","journal-title":"arXiv"},{"key":"B7","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXgboost: A scalable tree boosting system,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B8","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1108\/IJILT-03-2023-0043","article-title":"Detecting AI-generated essays: the ChatGPT challenge","volume":"40","author":"Cingillioglu","year":"2023","journal-title":"Int. J. Inform. Learn. Technol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.10555","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020","journal-title":"arXiv"},{"key":"B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN54540.2023.10191322","article-title":"\u201cA deep fusion model for human vs. machine-generated essay classification,\u201d","volume-title":"2023 International Joint Conference on Neural Networks (IJCNN)","author":"Corizzo","year":"2023"},{"key":"B11","doi-asserted-by":"publisher","first-page":"9","DOI":"10.5120\/20182-2402","article-title":"Applications of artificial intelligence in machine learning: review and prospect","volume":"115","author":"Das","year":"2015","journal-title":"Int. J. Comp. Appl"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv"},{"key":"B13","first-page":"103","article-title":"\u201cEvaluating quadratic weighted kappa as the standard performance metric for automated essay scoring,\u201d","volume-title":"16th International Conference on Educational Data Mining, EDM 2023","author":"Doewes","year":"2023"},{"key":"B14","first-page":"242","article-title":"\u201cIdentifying ChatGPT-generated essays against native and non-native speakers,\u201d","volume-title":"The International Conference on Artificial Intelligence and Smart Environment","author":"El Kah","year":"2023"},{"key":"B15","volume-title":"The Hewlett","author":"Hamner","year":"2012"},{"key":"B16","doi-asserted-by":"publisher","first-page":"18617","DOI":"10.1038\/s41598-023-45644-9","article-title":"A large-scale comparison of human-written versus ChatGPT-generated essays","volume":"13","author":"Herbold","year":"2023","journal-title":"Sci. Rep"},{"key":"B17","first-page":"393","article-title":"A review on detecting fake news through text classification","volume":"11","author":"Kaur","year":"2019","journal-title":"Int. J. Electron. Eng"},{"key":"B18","first-page":"3","article-title":"Advantages and disadvantages of artificial intelligence and machine learning: a literature review","volume":"9","author":"Khanzode","year":"2020","journal-title":"Int. J. Library Inform. Sci"},{"key":"B19","article-title":"\u201cParaphrasing evades detectors of ai-generated text, but retrieval is an effective defense,\u201d","author":"Krishna","year":"2024"},{"key":"B20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/NCC48643.2020.9056085","article-title":"\u201cA tfidfvectorizer and svm based sentiment analysis framework for text data corpus,\u201d","volume-title":"2020 National Conference on Communications (NCC)","author":"Kumar","year":"2020"},{"key":"B21","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1161\/CIRCULATIONAHA.106.682658","article-title":"Logistic regression","volume":"117","author":"LaValley","year":"2008","journal-title":"Circulation"},{"key":"B22","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"},{"key":"B23","first-page":"152","article-title":"\u201cClassification of human-and AI-generated texts: investigating features for ChatGPT,\u201d","volume-title":"International Conference on Artificial Intelligence in Education Technology","author":"Mindner","year":"2023"},{"key":"B24","first-page":"24950","article-title":"\u201cDetectGPT: zero-shot machine-generated text detection using probability curvature,\u201d","volume-title":"International Conference on Machine Learning","author":"Mitchell","year":"2023"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.06652","article-title":"\u201cLarge language model (LLM) AI text generation detection based on transformer deep learning algorithm,\u201d","author":"Mo","year":"2024","journal-title":"arXiv"},{"key":"B26","volume-title":"Artificial Intelligence-Based Text Classification: Separating Human Writing From Computer Generated Writing","author":"Morales-M\u00e1rquez","year":"2023"},{"key":"B27","article-title":"\u201cFake review detection: classification and analysis of real and pseudo reviews,\u201d","volume-title":"UIC-CS-03-2013 Technical Report","author":"Mukherjee","year":"2013"},{"key":"B28","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10805-023-09492-6","article-title":"Detection of GPT-4 generated text in higher education: combining academic judgement and software to identify generative AI tool misuse","volume":"22","author":"Perkins","year":"2024","journal-title":"J. Acad. Ethics"},{"key":"B29","doi-asserted-by":"publisher","author":"Sadasivan","year":"2023","DOI":"10.48550\/arXiv.2303.11156"},{"key":"B30","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/978-1-4899-7641-3_9","article-title":"\u201cSupport vector machine,\u201d","volume-title":"Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning","author":"Suthaharan","year":"2016"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.54254\/2753-8818\/39\/20240625","article-title":"AI-generated text detection and classification based on BERT deep learning algorithm","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"B32","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s40979-023-00146-z","article-title":"Testing of detection tools for AI-generated text","volume":"19","author":"Weber-Wulff","year":"2023","journal-title":"Int. J. Educ. Integrity"},{"key":"B33","first-page":"125","article-title":"Detection of AI-generated essays in writing assessment","volume":"65","author":"Yan","year":"2023","journal-title":"Psychol. Test. Assessm. Model"},{"key":"B34","doi-asserted-by":"publisher","first-page":"22502","DOI":"10.1609\/aaai.v38i20.30258","article-title":"Towards automatic boundary detection for human-AI collaborative hybrid essay in education","volume":"38","author":"Zeng","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intellig"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1469197\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T06:19:32Z","timestamp":1731997172000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1469197\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":34,"alternative-id":["10.3389\/frai.2024.1469197"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1469197","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,19]]},"article-number":"1469197"}}