Authors : Shruti Suhas Velhal; Dr. Pratibha Adkar

Volume/Issue : Volume 11 - 2026, Issue 5 - May

---

Google Scholar : https://tinyurl.com/3ds3c4n4

Scribd : https://tinyurl.com/3j929m5s

DOI : https://doi.org/10.38124/ijisrt/26May1449

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : This research paper focuses on detecting nuances in hybrid AI-generated academic essays by identifying subtle differences between human-written, AI-generated, and partially edited content. With the growing use of AI tools in education, traditional detection systems often fail to recognize essays that are generated by AI and later modified by humans. The proposed system uses Natural Language Processing and machine learning techniques to analyze writing style, sentence patterns, linguistic features, and factual consistency. It also generates a Naturalness Score to measure human-likeness. The system aims to improve detection accuracy, reduce false results, and support academic integrity in modern educational environments.

Keywords : Essay Submission, Text Preprocessing, Linguistic Analysis, Stuctural Analysis, Fact Verification, Feature Extraction and Combination, Machine learning Classification, Content Classification, Naturalness Score Generation, Report Generation and Log Storage.

References :

1. F. Oketunji, “Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text,” arXiv Preprint arXiv:2311.15565 , pp. 1–10, 2023.
2. H. Desaire, A. E. Chua, M. Isom, R. Jarosova, and D. Hua, “Distinguishing Academic Science Writing from Humans or ChatGPT with Over 99% Accuracy Using Off-the-Shelf Machine Learning Tools,” Cell Reports Physical Science, vol. 4, no. 6, Art. no. 101426, Jun. 2023.
3. D. Weber-Wulff, A. Anohina-Naumeca, S. Bjelobaba, T. Foltýnek, J. Guerrero-Dib, O. Popoola, P. Šigut, and L. Waddington, “Testing of Detection Tools for AI-Generated Text,” International Journal for Educational Integrity, vol. 19, no. 1, Art. no. 27, 2023.
4. S. Herbold , A. Hautli-Janisz, U. Heuer, Z. Kikteva, and A. Trautsch, “A Large-Scale Comparison of Human-Written Versus ChatGPT-Generated Essays,” Scientific Reports, vol. 13, Art. no. 18617, 2023.
5. Z. Zeng, S. Liu, L. Sha, Z. Li, K. Yang, S. Liu, D. Gašević, and G. Chen, “Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights,” in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI), pp. 7545–7553, 2024.
6. Y. Zhang, Q. Leng, M. Zhu, R. Ding, Y. Wu, J. Song, and Y. Gong, “Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection,” arXiv Preprint arXiv:2406.06558, pp. 1–15, 2024.
7. C. Mao, C. Vondrick, H. Wang, and J. Yang, “RAIDAR: geneRative AI Detection viA Rewriting,” arXiv Preprint arXiv:2401.12970, pp. 1–14, 2024.
8. G. P. Georgiou, “Differentiating Between Human-Written and AI-Generated Texts Using Automatically Extracted Linguistic Features,” Information, vol. 16, no. 11, Art. no. 979, 2025.
9. B. Jabarian and A. Imas, “Artificial Writing and Automated Detection,” NBER Working Paper Series, Working Paper no. 34223, pp. 1–46, 2025.
10. S. Dik and O. Erdem, “Assessing GPT-Zero’s Accuracy in Identifying AI vs. Human-Written Essays,” Proceedings of International Mathematical Sciences, vol. 7, no. 2, pp. 54–58, 2026.