Detecting AI-Generated Text in Educational Content: Leveraging Machine Learning and Explainable AI for Academic Integrity

作     者：Najjar, Ayat A. Ashqar, Huthaifa I. Darwish, Omar A. Hammad, Eman 

作者机构：Faculty of Modern Science Arab American University 13 Zababdeh P.O Box 240 Jenin Palestine Civil Engineering Department Arab American University 13 Zababdeh P.O Box 240 Jenin Palestine Artificial Intelligence Program Fu Foundation School of Engineering and Applied Science Columbia University 500 W 120th St New YorkNY10027 United States Information Security and Applied Computing Eastern Michigan University 900 Oakwood St YpsilantiMI48197 United States iSTAR Lab Engineering Technology & Industrial Distribution Texas A&M University 400 Bizzell St College StationTX77840 United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2025年

核心收录：

主　　题：Adversarial machine learning 

摘      要：This study seeks to enhance academic integrity by providing tools to detect AI-generated content in student work using advanced technologies. The findings promote transparency and accountability, helping educators maintain ethical standards and supporting the responsible integration of AI in education. A key contribution of this work is the generation of the CyberHumanAI dataset, which has 1000 observations, 500 of which are written by humans and the other 500 produced by ChatGPT. We evaluate various machine learning (ML) and deep learning (DL) algorithms on the CyberHumanAI dataset comparing human-written and AI-generated content from Large Language Models (LLMs) (i.e., ChatGPT). Results demonstrate that traditional ML algorithms, specifically XGBoost and Random Forest, achieve high performance (83% and 81% accuracies respectively). Results also show that classifying shorter content seems to be more challenging than classifying longer content. Further, using Explainable Artificial Intelligence (XAI) we identify discriminative features influencing the ML model s predictions, where human-written content tends to use a practical language (e.g., use and allow). Meanwhile AI-generated text is characterized by more abstract and formal terms (e.g., realm and employ). Finally, a comparative analysis with GPTZero show that our narrowly focused, simple, and fine-tuned model can outperform generalized systems like GPTZero. The proposed model achieved approximately 77.5% accuracy compared to GPTZero s 48.5% accuracy when tasked to classify Pure AI, Pure Human, and mixed class. GPTZero showed a tendency to classify challenging and small-content cases as either mixed or unrecognized while our proposed model showed a more balanced performance across the three classes. © 2025, CC BY.