Implementation of Machine Learning in the Classification of Text Created by Humans or Artificial Intelligence

Alexander Gosal, Riska Septifani

2025

Abstract

Rapid developments in the field of artificial intelligence have triggered significant advances in generative artificial intelligence technology, particularly large language models. These models, especially conversational artificial intelligence such as ChatGPT, have the potential to revolutionize various aspects of life. However, behind this potential lie dangers and concerns that need to be addressed. The model's ability to generate text that is highly similar to human written text raises concerns about the spread of fake news and misinformation. This research aims to implement a machine learning model to classify text generated by humans or AI. The research collected 6650 data points from the Philosophy Exchange website and the GPT-3.5 model, analyzing responses from 4109 user answers and 2541 GPT model responses. Philosophy Exchange is an online discussion platform where individuals engage in debates and knowledge-sharing on philosophical concepts, ethical dilemmas, and critical thinking questions. The XLNet model outperformed the SVM model by 0.03, achieving precision, recall, and F1 scores of 0.98. The XAI analysis showed that GPT-3.5 tends to use certain words more frequently, indicating a limited vocabulary and repetitive word usage patterns.

Paper Citation

in Harvard Style

Gosal A. and Septifani R. (2025). Implementation of Machine Learning in the Classification of Text Created by Humans or Artificial Intelligence. In Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH; ISBN 978-989-758-784-9, SciTePress, pages 45-52. DOI: 10.5220/0014269100004928

in Bibtex Style

@conference{ritech25,
author={Alexander Gosal and Riska Septifani},
title={Implementation of Machine Learning in the Classification of Text Created by Humans or Artificial Intelligence},
booktitle={Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH},
year={2025},
pages={45-52},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0014269100004928},
isbn={978-989-758-784-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Innovations in Information and Engineering Technology - Volume 1: RITECH
TI - Implementation of Machine Learning in the Classification of Text Created by Humans or Artificial Intelligence
SN - 978-989-758-784-9
AU - Gosal A.
AU - Septifani R.
PY - 2025
SP - 45
EP - 52
DO - 10.5220/0014269100004928
PB - SciTePress