Detecting AI-Generated Essays with Lexical Stylometric Features using Machine Learning
International Journal on Perceptive and Cognitive Computing · 30.07.2026 · 12 (2) · 11-18
DOI: 10.31436/ijpcc.v12i2.699 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal on Perceptive and Cognitive Computing, online erschienen am 30.07.2026. Verfasst von Tahmida Haque Sumbula und 2 weiteren Autor:innen.
Abstract (Originalsprache)
The increasing use of generative artificial intelligence (AI) in academic writing has intensified concerns about authorship authenticity. This study investigates whether lexical stylometric features alone can distinguish AI-generated essays from human-written essays. A balanced dataset of 200 undergraduate essays (100 AI-generated and 100 human-written) was analyzed using vocabulary richness measures, lexical density, word usage distributions, and word-level n-grams. Logistic Regression, Decision Tree, and Support Vector Machine classifiers were applied to evaluate performance. Results indicate that lexical features provide strong discriminatory capability across the three models with accuracy ranging between 90 – 97.5%, suggesting that effective AI authorship detection can be achieved without complex feature engineering or ensemble methods. The findings support the feasibility of a lightweight and interpretable detection framework for educational contexts.
Zitieren
APA
Sumbula, T. H., Sulaiman, S., & Ariffin, A. (2026). Detecting AI-Generated Essays with Lexical Stylometric Features using Machine Learning. International Journal on Perceptive and Cognitive Computing, 12(2), 11-18. https://doi.org/10.31436/ijpcc.v12i2.699
Vancouver
Sumbula TH, Sulaiman S, Ariffin A. Detecting AI-Generated Essays with Lexical Stylometric Features using Machine Learning. International Journal on Perceptive and Cognitive Computing. 2026;12(2):11-18. doi:10.31436/ijpcc.v12i2.699
BibTeX
@article{Sumbula2026,
author = {Sumbula, Tahmida Haque and Sulaiman, Suriani and Ariffin, Adlina},
title = {Detecting AI-Generated Essays with Lexical Stylometric Features using Machine Learning},
journal = {International Journal on Perceptive and Cognitive Computing},
year = {2026},
volume = {12},
number = {2},
pages = {11--18},
doi = {10.31436/ijpcc.v12i2.699}
}
EUVIMED