SOURCE-LINKED INTELLIGENCE

Detecting GPT-Assisted Writing Using Interpretable Stylometric Features

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Distinguishing GPT-assisted from independently authored student writing has become a critical challenge in academia. This paper evaluates the discriminative capability of interpretable stylometric features extracted solely from submitted text. Using data from 90 participants who wrote both independently and with ChatGPT assistance, we evaluate eight machine learning classifiers while keeping data from the same participant together during validation. On the held-out test set, Random Forest achieved an ROC-AUC of 0.87 and an F1-score of 0.84, with False Positive and False Negative rates of 22.2%

Read original source ↗ Open in workspace

recordType

paper

region

Global