Explainable Cyberbullying Detection for Multilingual Online Platforms Using NLP and Augmentation-Enhanced Deep Learning
Electronics · 04.11.2026 · 15 (21) · 5126
DOI: 10.3390/electronics15215126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 04.11.2026. Verfasst von Meghal Mandot und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The growing prevalence of online abuse has increased the need for automatic cyberbullying and hate speech detection, particularly in under-resourced and morphologically complex languages with limited annotated data and language resources. This study presents a multilingual English–Lithuanian framework combining machine learning, deep learning, transformer models, three data augmentation techniques, and explainable AI to address class imbalance, limited data, and model transparency. Overall, transformer-based approaches outperformed traditional methods. For the English dataset, averaged results over five runs with different random seeds showed model-dependent performance. Syn-Aug achieved the best F1-scores for LR (0.8791 ± 0.0029), SVM (0.8810 ± 0.0028), and RoBERTa (0.9287 ± 0.0023), while contextual BERT augmentation achieved the best F1-scores for CNN (0.9124 ± 0.0020) and BERT (0.9274 ± 0.0021). The highest English performance was obtained with the soft-voting BERT-RoBERTa ensemble, with an F1-score of 0.9356 ± 0.0035. For Lithuanian hate speech classification, hold-out validation and five-fold cross-validation were employed and evaluated on the same independent test set. For the five-fold cross-validation, XLM-RoBERTa and Syn-Aug achieved the best accuracy (0.9458) and F1-score (0.9363), followed by XLM-RoBERTa with XLM-Aug (accuracy 0.9072; F1-score 0.9336). Under the hold-out protocol, XLM-RoBERTa with XLM-Aug achieved the best accuracy (0.824) and F1-score (0.8109). These results show that Lithuanian classification performance varied with augmentation and evaluation protocol. Cross-language transfer using semantically aligned binary labels further highlighted the importance of language-specific data. Overall, the proposed approach supports efficient, interpretable, and reliable multilingual cyberbullying detection.
Zitieren
APA
Mandot, M., Abayomi-Alli, O. O., Goranin, N., & Abayomi-Alli, A. A. (2026). Explainable Cyberbullying Detection for Multilingual Online Platforms Using NLP and Augmentation-Enhanced Deep Learning. Electronics, 15(21), 5126. https://doi.org/10.3390/electronics15215126
Vancouver
Mandot M, Abayomi-Alli OO, Goranin N, Abayomi-Alli AA. Explainable Cyberbullying Detection for Multilingual Online Platforms Using NLP and Augmentation-Enhanced Deep Learning. Electronics. 2026;15(21):5126. doi:10.3390/electronics15215126
BibTeX
@article{Mandot2026,
author = {Mandot, Meghal and Abayomi-Alli, Olusola Oluwakemi and Goranin, Nikolaj and Abayomi-Alli, Adebayo Adewumi},
title = {Explainable Cyberbullying Detection for Multilingual Online Platforms Using NLP and Augmentation-Enhanced Deep Learning},
journal = {Electronics},
year = {2026},
volume = {15},
number = {21},
pages = {5126},
doi = {10.3390/electronics15215126}
}
EUVIMED