Hybrid Lexicon–Cyberbert Abusive Content Reporting Algorithm (HLCA) for Online Harassment Detection and Evidence-Aware Mitigation

DOI

10.2991/978-94-6239-616-6_114How to use a DOI?

Keywords

Cyber harassment detection; CyberBERT; Hybrid detection; Adversarial robustness; Evidence collection; Deep learning; Abusive content detection

Abstract

Cyber harassment is a significant concern for victims of dig ital communication platforms. Systematically compiling evidence that is legally acceptable is an insurmountable challenge for victims. Most traditional detection methods fail because harassment tactics evolve, abuse language is contextually dependent, and there are methods for adversarial evasion. In this paper, we introduce a novel Hybrid Lexicon CyberBERTAbusive Content Reporting Algorithm (HLCA) that merges rule-based lexicon matching and deep learning approaches to contextual understanding of cyber harassment. In proposed systems, gaps in approaches are closed by leveraging adversarial robustness, real-time detection of cyber harassment, and generating legally structured evidence documenting the harassment. CyberBERT, a domain-specific model pre trained on cyberbullying and online abuse with lexicon-based filtering and harassment patterns is the core of our detection module. By incorporating deep learning-based contextual understanding, we bridge the gaps in cyber harassment detection systems. Our extensive experimental evaluable on canonical datasets shows that HLCA or Hybrid Lexicon CyberBERT Abusive Content Reporting Algorithm, achieves optimal results at 94.3% accuracy, 92.7% precision, and 91.8% recall. The system even outperforms the state of the art by 6-8%.

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  - K. Rajasri
AU  - R. Radhee
AU  - B. Monika
AU  - M. Lavanya
PY  - 2026
DA  - 2026/03/31
TI  - Hybrid Lexicon–Cyberbert Abusive Content Reporting Algorithm (HLCA) for Online Harassment Detection and Evidence-Aware Mitigation
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1612
EP  - 1627
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_114
DO  - 10.2991/978-94-6239-616-6_114
ID  - Rajasri2026
ER  -