Deep Fake Detection for Identifying Machine Generated Tweets Using NLP and DL

G. Shabana, E. Madhuri, A. Nadeem, D. Charan Kumar Reddy, Y. Harshavardhan Lourdu Reddy

2025

Abstract

The rise of advanced natural language generation models has led to an increasing prevalence of deepfake content on social media, particularly machine-generated tweets designed to manipulate public opinion. This research presents a deep learning-based approach for detecting AI-generated tweets using a Convolutional Neural Network (CNN) combined with FastText word embeddings. The proposed model outperforms baseline machine learning methods that utilize Term Frequency (TF), Term Frequency-Inverse Document Frequency (TF-IDF), and traditional FastText embeddings. Experimental results demonstrate the superior accuracy of the CNN-FastText model in distinguishing human-written tweets from bot-generated ones. This study contributes to combating misinformation and enhancing online discourse integrity by providing an effective and scalable detection mechanism.

Paper Citation

in Harvard Style

Shabana G., Madhuri E., Nadeem A., Reddy D. and Reddy Y. (2025). Deep Fake Detection for Identifying Machine Generated Tweets Using NLP and DL. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 507-511. DOI: 10.5220/0013915700004919

in Bibtex Style

@conference{icrdicct`2525,
author={G. Shabana and E. Madhuri and A. Nadeem and D. Reddy and Y. Reddy},
title={Deep Fake Detection for Identifying Machine Generated Tweets Using NLP and DL},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={507-511},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013915700004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Deep Fake Detection for Identifying Machine Generated Tweets Using NLP and DL
SN - 978-989-758-777-1
AU - Shabana G.
AU - Madhuri E.
AU - Nadeem A.
AU - Reddy D.
AU - Reddy Y.
PY - 2025
SP - 507
EP - 511
DO - 10.5220/0013915700004919
PB - SciTePress