AI vs. Human Writing: Developing a Novel Method for Text Authenticity Detection in Education
Open accessAbstract
Rapid progress in generative artificial intelligence (AI) technologies has brought forth stupendous challenges in differentiating AI-written text from human text.The Naturalness Score, a composite measure that considers lexical diversity, syntactic complexity, sentiment variability, and grammatical faults, is a new idea that emerged from this study.The Naturalness score is part of a larger machine learning framework, although it does have an individual classifier called the Naturalness-Based Logistic Regression Classifier or NLRC.The NLRC model was analyzed against a large, diverse corpus of nearly 45,000 text samples, most of which were student essays, articles, and web-scraped content.The proposed model outperformed all existing baseline models with an accuracy of 96.41%, precision of 0.98, recall of 0.95, and F1 score of 0.96.The high areas under the receiver operating characteristic curve (AUC=1.00)and precision-recall curve (AUC-PR) also indicate the effectiveness of the model in differentiating AI generated from human-written text.Volume 17 (2025), Issue 3The proposed approach offers several advantages including increased detection accuracy, resilience against AIgenerated content, cross-domain applicability, and interpretability.The research has implications for applying such models in schools, although it also calls for future research on the implications of the rapidly changing landscape of AIgenerated content which it states.It emphasizes the importance of these findings in developing robust and adaptive detection systems to ensure the integrity of academic assessments, thereby preventing the misuse of AI tools.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Generative AI tools allow students to automatically generate essays, reports, and coding solutions, increasing the risk of plagiarism and contract cheating.
“These tools allow students to automatically gen -erate essays, reports, and coding solutions, increasing the risk of plagiarism and contract cheating [ 55, 56, 79-81].”
From Redefining student assessment in AI-infused learning environments: a systematic review of challenges and strategies for academic integrity (2026) · cites this paper as [79]
The Introduction (page not provided) says students use AI tools to write essays and generate code, often without disclosing their use. The Literature Review and the ‘Support for Teachers and Institution’ section connect AI-generated submissions with plagiarism and academic-honesty concerns. The passages do not specifically address student reports or contract cheating. (LLM, conf=0.85)
Experimental — accuracy not yet measuredInstitutions have shifted toward alternative assessment methods, such as oral exams (viva voce), real-world reflective tasks, scaffolded assignments, reflective journals, Bloom's Taxonomy higher-order thinking questions, and interactive problem-solving tasks, which require direct student engagement and cannot be easily outsourced to AI.
“To achieve this, institutions have shifted toward alternative assessment methods, such as oral exams (viva voce), real-world reflective tasks, scaffolded assignments, reflective journals, use of Bloom's Taxonomy higher-order thinking questions, and interactive problemsolving tasks, which require direct student engagement and cannot be easily outsourced to AI [ 56, 65, 67, 70, 73, 79, 89, 94, 97-99”
From Redefining student assessment in AI-infused learning environments: a systematic review of challenges and strategies for academic integrity (2026) · cites this paper as [79]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
ChatGPT for good? On opportunities and challenges of large language models for education
Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., Günnemann, S., Hüllermeier, E., et al. (2023) · Learning and Individual Differences · doi:10.1016/j.lindif.2023.102274 · Cited by 7,326 · see citing works
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653 · see citing works
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan, V., Ahuja, M., et al. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102642 · Cited by 4,584 · see citing works
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · see citing works
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083 · see citing works
AI-generated research paper fabrication and plagiarism in the scientific community
Elali, F. R., & Rachid, L. N. (2023) · Patterns · doi:10.1016/j.patter.2023.100706 · Cited by 197 · see citing works
Pentina, I., Xie, T., Hancock, T. D., & Bailey, A. A. (2023) · Psychology and Marketing · doi:10.1002/mar.21853 · Cited by 195 · see citing works
Bernabei, M., Colabianchi, S., Falegnami, A., & Costantino, F. (2023) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2023.100172 · Cited by 175 · see citing works
AI-generated vs human-authored texts: A multidimensional comparison
Berber Sardinha, T. (2024) · Applied Corpus Linguistics · doi:10.1016/j.acorp.2023.100083 · Cited by 139 · see citing works
Do teachers spot AI? Evaluating the detectability of AI-generated texts among student essays
Fleckenstein, J., Meyer, J., Jansen, T., Keller, S. D., Köller, O., & Möller, J. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100209 · Cited by 126 · see citing works
A Survey on Detection of LLMs-Generated ContentPreprint
Yang, X., Pan, L., Zhao, X., Chen, H.-F., Petzold, L., Wang, W. Y., & Cheng, W. (2023) · Conference on Empirical Methods in Natural Language Processing · doi:10.48550/arxiv.2310.15654 · Cited by 108 · see citing works
Nasution, A. H., & Onan, A. (2024) · IEEE Access · doi:10.1109/access.2024.3402809 · Cited by 105 · see citing works
Barman, D., Guo, Z., & Conlan, O. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100545 · Cited by 103 · see citing works
Can large language models write reflectively
Li, Y., Sha, L., Yan, L., Lin, J., Raković, M., Galbraith, K., Lyons, K., Gašević, D., & Chen, G. (2023) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2023.100140 · Cited by 99 · see citing works
Enhancing large language model capabilities for rumor detection with Knowledge-Powered Prompting
Yan, Y., Zheng, P., & Wang, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108259 · Cited by 66 · see citing works
Distinguishing Human-Written and ChatGPT-Generated Text Using Machine Learning
Alamleh, H., AlQahtani, A. A. S., & ElSaid, A. A. (2023) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds58326.2023.10137767 · Cited by 64 · see citing works
Evaluating Human-Language Model Interaction
Lee, M., Srivastava, M., Hardy, A., Thickstun, J., Durmus, E., Paranjape, A., Gerard-Ursin, I., Li, X. L., Ladhak, F., Rong, F., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.09746 · Cited by 61 · see citing works
Between human and AI: assessing the reliability of AI text detection tools
Bellini, V., Semeraro, F., Montomoli, J., Cascella, M., & Bignami, E. (2024) · Current Medical Research and Opinion · doi:10.1080/03007995.2024.2310086 · Cited by 60 · see citing works
Dinh, T. L., Le, T. D., Uwizeyemungu, S., & Pelletier, C. (2025) · Information · doi:10.3390/info16030240 · Cited by 50 · see citing works
Accurately detecting AI text when ChatGPT is told to write like a chemist
Desaire, H., Chua, A. E., Kim, M., & Hua, D. (2023) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2023.101672 · Cited by 47 · see citing works
How Far Have We Gone in Vulnerability Detection Using Large Language ModelsPreprint
Gao, Z., Wang, H., Zhou, Y., Zhu, W., & Zhang, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.12420 · Cited by 43 · see citing works
A Linguistic Comparison between Human and ChatGPT-Generated ConversationsPreprint
Sandler, M., Choung, H., Ross, A., et al. (2024) · International Conferences on Pattern Recognition and Artificial Intelligence · doi:10.48550/arxiv.2401.16587 · Cited by 42 · see citing works
Adapting Fake News Detection to the Era of Large Language Models
Su, J., Cardie, C., & Nakov, P. (2024) · Findings of the Association for Computational Linguistics: NAACL 2024 · doi:10.18653/v1/2024.findings-naacl.95 · Cited by 42 · see citing works
A Survey on Detection of LLMs-Generated Content
Yang, X., Pan, L., Zhao, X., Chen, H., Petzold, L. R., Wang, W. Y., & Cheng, W. D. (2024) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2024.findings-emnlp.572 · Cited by 41 · see citing works
An evaluation on large language model outputs: Discourse and memorization
de Wynter, A., Wang, X., Sokolov, A., Gu, Q., & Chen, S. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100024 · Cited by 39 · see citing works
Who Wrote This?: Detecting Artificial Intelligence–Generated Text from Human-Written Text
Kumar, R., & Mindzak, M. (2024) · Canadian Perspectives on Academic Integrity · doi:10.55016/ojs/cpai.v7i1.77675 · Cited by 38 · see citing works
Rasool, Z., Kurniawan, S., Balugo, S., Barnett, S., Vasa, R., Chesser, C., Hampstead, B. M., Belleville, S., Mouzakis, K., & Bahar-Fuchs, A. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2024.100083 · Cited by 34 · see citing works
Augmenting assessment with AI coding of online student discourse: A question of reliability
Misiejuk, K., Kaliisa, R., & Scianna, J. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100216 · Cited by 33 · see citing works
Flitcroft, M. A., Sheriff, S. A., Wolfrath, N., Maddula, R., McConnell, L., Xing, Y., Haines, K., Wong, S. L., & Kothari, A. N. (2024) · Annals of Surgical Oncology · doi:10.1245/s10434-024-15549-6 · Cited by 33 · see citing works
AI vs humans in the AUT: Simulations to LLMs
Gilhooly, K. J. (2023) · Journal of Creativity · doi:10.1016/j.yjoc.2023.100071 · Cited by 32 · see citing works
Unveiling ChatGPT text using writing style
Berriche, L., & Larabi-Marie-Sainte, S. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e32976 · Cited by 31 · see citing works
Faculty of Computing and Information Technology, K. A. U., Alshahrani, K., & Jameel Qureshi, R. (2024) · International Journal of Modern Education and Computer Science · doi:10.5815/ijmecs.2024.04.06 · Cited by 31 · see citing works
A Linguistic Comparison Between Human and ChatGPT-Generated Conversations
Sandler, M., Choung, H., Ross, A. A., & David, P. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8702-9_25 · Cited by 29 · see citing works
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
Jiang, H., Chen, L., Wang, C., & Zhao, T. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.165 · Cited by 27 · see citing works
Unsupervised and Distributional Detection of Machine-Generated TextPreprint
Gallé, M., Rozen, J., Kruszewski, G., & Elsahar, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02878 · Cited by 27 · see citing works
Spam detection for Youtube video comments using machine learning approaches
Xiao, A. S., & Liang, Q. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100550 · Cited by 22 · see citing works
Silva, G. S., Khera, R., Schwamm, L. H., Acampa, M., Adelman, E. E., Boltze, J., Broderick, J. P., Brodtmann, A. G., Christensen, H., Dalli, L. L., et al. (2024) · Stroke · doi:10.1161/strokeaha.124.045012 · Cited by 19 · see citing works
Use prompt to differentiate text generated by ChatGPT and humans
An, R., Yang, Y., Yang, F., & Wang, S. (2023) · Machine Learning with Applications · doi:10.1016/j.mlwa.2023.100497 · Cited by 17 · see citing works
AI or Human? Finding and Responding to Artificial Intelligence in Student Work
Fisk, G. D. (2024) · Teaching of Psychology · doi:10.1177/00986283241251855 · Cited by 16 · see citing works
Early Formalization of AI-tools Usage in Software Engineering in Europe: Study of 2023
Software engineering domain, A., & Pashchenko, D. S. (2023) · International Journal of Information Technology and Computer Science · doi:10.5815/ijitcs.2023.06.03 · Cited by 14 · see citing works
An Applied Statistics dataset for human vs AI-generated answer classification
Salim, M. S., & Hossain, S. I. (2024) · Data in Brief · doi:10.1016/j.dib.2024.110240 · Cited by 13 · see citing works
Singh, A., Sharma, D., Nandy, A., & Singh, V. K. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100050 · Cited by 11 · see citing works
C-Net: A Compression-Based Lightweight Network for Machine-Generated Text Detection
Zhou, Y., Wen, J., Jia, J., Gao, L., & Zhang, Z. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3394264 · Cited by 11 · see citing works
Do I Write Like Artificial Intelligence?
Mondal, H. (2024) · Annals of Surgical Oncology · doi:10.1245/s10434-024-16480-6 · Cited by 11 · see citing works
LLMs Performance on Vietnamese High School Biology Examination
Dao, X.-Q., & Le, N.-B. (2023) · International Journal of Modern Education and Computer Science · doi:10.5815/ijmecs.2023.06.02 · Cited by 10 · see citing works
Adapting Fake News Detection to the Era of Large Language ModelsPreprint
Su, J., Cardie, C., & Nakov, P. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.04917 · Cited by 5 · see citing works
Harnessing Large Language Models for Effective and Efficient Hate Speech Detection
Svetasheva, A., & Lee, K. (2024) · Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences · doi:10.24251/hicss.2024.826 · Cited by 4 · see citing works
AHAM: Adapt, Help, Ask, Model Harvesting LLMs for Literature Mining
Koloski, B., Lavrač, N., Cestnik, B., Pollak, S., Škrlj, B., & Kastrin, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58547-0_21 · Cited by 4 · see citing works
AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature miningPreprint
Koloski, B., Lavrač, N., Cestnik, B., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.15784 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Ncube, P. D. N., Dzvapatsva, G. P., Matobobo, C., & Ranga, M. M. (2026) · AI and Ethics · doi:10.1007/s43681-025-00871-w · Cited by 31 · see citing works
“…reflective tasks, scaffolded assignments, reflective journals, use of Bloom's Taxonomy higher-order thinking questions, and interactive problem-solving tasks, which require direct student engagement and cannot be easily outsourced to AI [ 56, 65, 67, 70, 73, 79, 89, 94, 97–99, 101, 102 ].”
Gao, S., Yang, H., & Fan, W. (2025) · IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) · doi:10.1109/idaacs68557.2025.11322164
The Emotional Signature: Detecting AI-Generated Short Stories through Narrative and Emotion Analysis
Zummon, S. A., Khan, A. B., Mim, T. A., & Sumiya, S. T. (2026) · International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) · doi:10.1109/icecte69292.2026.11429356
Migdady, A., & Alshalabi, R. (2026) · International Conference on Smart Multidomain Integrated Learning Environments (ICSMILE) · doi:10.1109/icsmile69273.2026.11519159
Detecting “large language models fingerprint” for Japanese texts generated by six LLMs
Zaitsu, W., Jin, M., Ishihara, S., Tsuge, S., & Inaba, M. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1771115
Deepfake Detection of AI-Generated Text and Images Using Deep Learning
Gnanakumar, D., Kula Theja, G., Harsha Vardhan, G., Thrinath, K., & Chaithanya, K. (2026) · International Conference on Innovations in Emerging Technologies for Sustainable Development (ICIETSD) · doi:10.1109/icietsd68684.2026.11584726
Khlaif, Z. N., Hamamra, B. T., Farran, H. K., & Salama, N. (2026) · Journal of Academic Ethics · doi:10.1007/s10805-026-09768-7
- Authors
- Department of Computer Science and Engineering, R. I. O. T., Kalmani, V. H., Adamuthe, A. C., Premnath Gondil, A., Prashant Patil, V., Amar Kore, R., & Mahadev Metkari, V.
- Affiliations
- Shivaji University (IN)
- Venue
- International Journal of Modern Education and Computer Science
- Publisher
- MECS Publisher
- Published
- 2025-06-08
- Volume
- 17
- Issue
- 3
- Pages
- 45-58
- ISSN
- 2075-0161 (ISSN-L)
- 2075-017X
- OpenAlex
- W4410939943
- Cited by
- 7
- References
- 44
- Citations by year
- 2026: 5 · 2025: 2
- FWCI
- 2.83
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- International Journal of Modern Education and Computer Science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Safety Research › Academic integrity and plagiarism
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- AI-generated text detection, lexical diversity, syntactic complexity, grammatical errors, logistic regression classifier, student essays, academic integrity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
