An explainable context-aware BERT-based hybrid cyberbullying detection model
The Computer Journal · 10.08.2026
DOI: 10.1093/comjnl/bxag083 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 10.08.2026. Verfasst von Shalini Agrahari und 1 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben.
Abstract (Originalsprache)
Due to too much ambiguity and lexical overlap in today’ social media texts, cyberbullying detection has been difficult. To detect cyberbullying contents and address gaps, a hybrid decoding-enhanced bidirectional encoder representations from transformers (BERT) with disentangled attention-bidirectional gated recurrent unit (DeBERTa-BiGRU)-Attention model (explainable context-aware cyberbullying BERT-based hybrid model) is proposed for multiclass classification, which outperformed baseline approaches across different metrics. DeBERTa model is used to model content and positional embeddings and enable fine-grained contextual representation; it utilizes disentangled attention with improved relative positional encoding. BiGRU is utilized resulting embeddings from DeBERTa, for sequential dependency and capturing bidirectional token relations. A token-level attention layer is used on top of these models for prioritizing both enhancing interpretability and predicting performance. The sequential integration of all three techniques together complements recurrent modeling with the transformer model, yielding a +4.2% F1-score over standalone DeBERTa. In this study, explainability evaluation demonstrates a high alignment between attention weights and gradient-based importance scores at the token level to preserve faithfulness. An efficient and comprehensible framework for fine-grained multi-class cyberbullying detection is provided by combining DeBERTa with BiGRU and an Attention layer, as demonstrated by experiments.
Zitieren
APA
Agrahari, S., & Tiwari, A. K. (2026). An explainable context-aware BERT-based hybrid cyberbullying detection model. The Computer Journal. https://doi.org/10.1093/comjnl/bxag083
Vancouver
Agrahari S, Tiwari AK. An explainable context-aware BERT-based hybrid cyberbullying detection model. The Computer Journal. 2026. doi:10.1093/comjnl/bxag083
BibTeX
@article{Agrahari2026,
author = {Agrahari, Shalini and Tiwari, Arvind K},
title = {An explainable context-aware BERT-based hybrid cyberbullying detection model},
journal = {The Computer Journal},
year = {2026},
doi = {10.1093/comjnl/bxag083}
}
EUVIMED