Hybrid Lexicon–Cyberbert Abusive Content Reporting Algorithm (HLCA) for Online Harassment Detection and Evidence-Aware Mitigation
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.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 ap proaches are closed by leveraging adversarial robustness, real-time de tection 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 incor porating 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 sys tem even outperforms the state of the art by 6-8%.
Fields of Study & Subjects
Hate Speech and Cyberbullying Detection
Spam and Phishing Detection
Misinformation and Its Impacts
Publication details
- Journal / source
- Advances in intelligent systems research/Advances in Intelligent Systems Research
- Pages
- 1612–1627
- Publication date
- 1 April 2026
- Language
- EN
- Document type
- Book chapter