English

StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features

Computation and Language 2025-07-17 v1 Artificial Intelligence Machine Learning

Abstract

This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generated texts for the classifier's training. We explore several parameter options to increase the classifier's capacity and take advantage of that training set. Our approach follows the non-neural, computationally inexpensive but explainable approach found effective previously.

Keywords

Cite

@article{arxiv.2507.12064,
  title  = {StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features},
  author = {Jeremi K. Ochab and Mateusz Matias and Tymoteusz Boba and Tomasz Walkowiak},
  journal= {arXiv preprint arXiv:2507.12064},
  year   = {2025}
}
R2 v1 2026-07-01T04:03:53.145Z