Open access
Sep 2026
Comparative Analysis of Transformer-Based and ClassicalMachine Learning Models for Phishing Email Detection:A Multi-Source Dataset Evaluation with Explainability
This paper compares five classifiers: Multinomial Naive Bayes, Random Forest, Bidirectional Long Short-Term Memory, BiLSTM, DistilBERT, and BERT-base, and finds that BERT-base achieves the highest F1-score and DistilBERT the lowest, representing the strongest accuracy–latency trade-off in the evaluated environment.
Andre Sebastian Samaniego Buñay, Ariel Misael Orellana Albarracin, Joel Marcelo Chuquimarca Pomagualli
· Enfoque UTE · 0 citations