EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive multilingual cyberbullying detection via grammatical evolution

Walaa Saber Ismail, Hikmat Ullah, Muhammad Adnan, Farman Ullah

PeerJ Computer Science · 28.04.2026 · 12 · e3740

DOI: 10.7717/peerj-cs.3740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 28.04.2026. Verfasst von Walaa Saber Ismail und 3 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Unit at Liwa University Under the Internal Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of digital communication has made social media an integral part of daily life, yet it has simultaneously amplified the reach of harmful behaviors. Early detection of cyberbullying is recognized as a critical safeguard for mental health, particularly for vulnerable demographics. Deep learning models, specifically multilingual transformers, are currently widely used as the most effective tools for automating toxicity detection across diverse languages. However, the interpretation of multilingual abuse is a complex multi-parameter process that frequently leads to false-positive and false-negative results. Static architectures often fail to capture evolving adversarial patterns, such as code-switching and dialectal sarcasm ( e.g ., the ironic use of حلوة أوي “very sweet”), and frequently reproduce algorithmic biases against protected groups. This article introduces a novel adaptive framework that synergizes Grammatical Evolution (GE) with hybrid multilingual embeddings to classify cyberbullying content with high precision and fairness. Distinct from traditional fixed architectures, our approach utilizes GE as an evolutionary optimizer to autonomously search the topological space of bidirectional long short-term memory (BiLSTM) classifiers, tailoring neural structures to the semantic richness of hybrid XLM-R and multilingual bidirectional encoder representations from transformers (mBERT) representations. Furthermore, a fairness-constrained fitness function is integrated to explicitly mitigate algorithmic bias during the optimization process. Experimental evaluation on the ArCyC Arabic corpus and the Fine-Grained Balanced English dataset demonstrates that this evolutionary-deep learning hybrid achieves a state-of-the-art F1-score of 0.9458. Crucially, the framework reduces subgroup performance disparities across age, gender, and religion by 41%, validating that ethical alignment can be mathematically integrated into the learning process without compromising predictive accuracy.

Förderung

  • Research Unit at Liwa University Under the Internal Research

Zitieren

APA

Ismail, W. S., Ullah, H., Adnan, M., & Ullah, F. (2026). Adaptive multilingual cyberbullying detection via grammatical evolution. PeerJ Computer Science, 12, e3740. https://doi.org/10.7717/peerj-cs.3740

Vancouver

Ismail WS, Ullah H, Adnan M, Ullah F. Adaptive multilingual cyberbullying detection via grammatical evolution. PeerJ Computer Science. 2026;12:e3740. doi:10.7717/peerj-cs.3740

BibTeX
@article{Ismail2026,
  author = {Ismail, Walaa Saber and Ullah, Hikmat and Adnan, Muhammad and Ullah, Farman},
  title = {Adaptive multilingual cyberbullying detection via grammatical evolution},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e3740},
  doi = {10.7717/peerj-cs.3740}
}
Kostenlos starten →