Comprehensive Survey on Adaptive Detection of Cyberbullying and Hate Speech using Natural Language Processing (NLP)

DOI

10.2991/978-94-6239-616-6_57How to use a DOI?

Keywords

Cyberbullying; Hate Speech; NLP; Machine Learning; Deep Learning; Neutrosophic Logic; Large Language Models (LLMs); OCR; Multimodal Analysis; Adaptive Detection

Abstract

Cyberbullying has emerged as one of the biggest challenges of the era, where social media platforms provide anonymity and speed that often fuel harmful interactions. Victims of such behaviour face significant emotional and psychological consequences, including anxiety, depression, and self-harm. Detecting cyberbullying automatically remains difficult because online communication is highly informal, filled with sarcasm, slang, memes, and ambiguous expressions that traditional machine learning models fail to interpret effectively. Existing systems, including models based on MultiLayer Perceptrons integrated with Neutrosophic Logic, have shown progress by addressing uncertainty and classifying cyberbullying into fine-grained categories such as age, gender, and religion. However, these approaches still fall short when confronted with implicit hate speech, multimodal content, and evolving online trends. This survey explores the groundwork of Neutrosophic Logic combined with neural networks, while highlighting the limitations of purely text-based classification. Furthermore, it discusses advancements that leverage Large Language Models like GPT and LLaMA, which capture deeper linguistic context and sarcasm, along with Optical Character Recognition (OCR) to extend detection into memebased hate speech. The paper explains the importance of multimodal, context-aware approaches for future systems, offering a pathway toward accurate, adaptable, and reliable solutions to combat cyberbullying-related hate speech.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - T. Maheshwaran
AU  - A. Sreram
AU  - G. Karthik Charan
AU  - Mohamed Imran Mi
PY  - 2026
DA  - 2026/03/31
TI  - Comprehensive Survey on Adaptive Detection of Cyberbullying and Hate Speech using Natural Language Processing (NLP)
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 757
EP  - 768
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_57
DO  - 10.2991/978-94-6239-616-6_57
ID  - Maheshwaran2026
ER  -