Leveraging Deep Neural Networks for Real-Time Detection of Cyberbullying and Offensive Memes in Social Network

K. Jayasurya, T. Periyasamy, S. Prasanth, S. Sibhisaran, A. Ananya

2025

Abstract

Although connection to other people is possible through the use of social media, the result has been what the social media users use to call as freedom of speech, which means that hate speech is also possible, and cyber bullying. Free speech has come to mean liberty to post vengeful memes or to harass individuals or groups based on their gender, colour, or religion. To locate such risky content, this study recommends a two-part approach that involves natural language processing and optical character recognition. The model takes textual and the visual input through deep neural recognition and analyses the sentiment of the text through a sentiment recognition dictionary and a sentiment estimator. Negative content is filtered according to script and feedback provided by the users of the application. When implemented on social media networks, these insights, which are delivered in real-time, can significantly improve the fight against the use of technology to perpetrate abuse.

Paper Citation

in Harvard Style

Jayasurya K., Periyasamy T., Prasanth S., Sibhisaran S. and Ananya A. (2025). Leveraging Deep Neural Networks for Real-Time Detection of Cyberbullying and Offensive Memes in Social Network. 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 69-74. DOI: 10.5220/0013908200004919

in Bibtex Style

@conference{icrdicct`2525,
author={K. Jayasurya and T. Periyasamy and S. Prasanth and S. Sibhisaran and A. Ananya},
title={Leveraging Deep Neural Networks for Real-Time Detection of Cyberbullying and Offensive Memes in Social Network},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={69-74},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013908200004919},
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 - Leveraging Deep Neural Networks for Real-Time Detection of Cyberbullying and Offensive Memes in Social Network
SN - 978-989-758-777-1
AU - Jayasurya K.
AU - Periyasamy T.
AU - Prasanth S.
AU - Sibhisaran S.
AU - Ananya A.
PY - 2025
SP - 69
EP - 74
DO - 10.5220/0013908200004919
PB - SciTePress