EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced social media phishing detection model using LSTM and BERT

Wenni Syafitri, Eddisyah Putra Pane, Edi Purwanto

Science, Technology, and Communication Journal · 28.02.2026 · 6 (2) · 165-174

DOI: 10.59190/stc.v6i2.360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, Technology, and Communication Journal, online erschienen am 28.02.2026. Verfasst von Wenni Syafitri und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Phishing attacks are a major cyber threat, with more than 30% of incidents occurring via social media platforms, especially short message services. This study evaluates deep learning approaches for automated phishing detection using BERT and Hybrid (BERT-LSTM) architectures fine-tuned on 15950 annotated SMS. The BERT-only model achieved superior performance (F1 0.9928, recall 0.9952, AUC 0.999) with no statistically significant improvement from adding BiLSTM layers (0.0006). K-fold cross-validation demonstrated robust generalisation (coefficient of variation 0.10%). Dataset saturation analysis indicated that 15,950 SMS are sufficient for effective transfer learning. Mild overfitting (6.3x loss ratio) remained within acceptable bounds and did not affect validation metrics. The 1.77% false positive rate and 99.52% recall enable practical deployment for production phishing defence. Results demonstrate that transfer learning with BERT achieves production-grade performance while challenging conventional assumptions about architectural complexity.

Zitieren

APA

Syafitri, W., Pane, E. P., & Purwanto, E. (2026). Enhanced social media phishing detection model using LSTM and BERT. Science, Technology, and Communication Journal, 6(2), 165-174. https://doi.org/10.59190/stc.v6i2.360

Vancouver

Syafitri W, Pane EP, Purwanto E. Enhanced social media phishing detection model using LSTM and BERT. Science, Technology, and Communication Journal. 2026;6(2):165-174. doi:10.59190/stc.v6i2.360

BibTeX
@article{Syafitri2026,
  author = {Syafitri, Wenni and Pane, Eddisyah Putra and Purwanto, Edi},
  title = {Enhanced social media phishing detection model using LSTM and BERT},
  journal = {Science, Technology, and Communication Journal},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {165--174},
  doi = {10.59190/stc.v6i2.360}
}
Kostenlos starten →