• Home
  • Search
  • Cross-lingual SMS spam detection using GAN-based augmentation for imbalanced datasets.
  • https://doi.org/10.1038/s41598-026-37769-4Copy DOI Icon

Cross-lingual SMS spam detection using GAN-based augmentation for imbalanced datasets.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

SMS spam detection remains a critical challenge in mobile communication security, particularly when addressing the inherent class imbalance present in real-world datasets, where spam messages constitute only 13–15% of total communications. This study presents a comprehensive framework integrating advanced word embeddings, deep learning architectures, and Generative Adversarial Networks (GANs) for synthetic data augmentation to enhance SMS spam classification performance. A systematic evaluation is conducted across six machine learning algorithms (Support Vector Machine (SVM), Logistic Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Stochastic Gradient Descent (SGD), Random Forest (RF)) and two deep learning models (Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM)), combined with five embedding techniques (Term Frequency–Inverse Document Frequency (TF-IDF), Bag of Words (BoW), Word2Vec, GloVe, Bidirectional Encoder Representations from Transformers (BERT)), resulting in 120 experimental configurations tested both with and without data augmentation. A novel GAN-based approach is employed to generate synthetic word embeddings rather than raw text, preserving semantic coherence while addressing dataset imbalance more effectively than traditional oversampling methods (Synthetic Minority Over-sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN)). Experimental validation on both the monolingual UCI SMS Spam Collection and multilingual datasets demonstrates that the optimal BERT+Bi-LSTM+GAN configuration achieves exceptional performance, with F1-scores of 97.61% (monolingual) and 94.44% (multilingual), surpassing existing state-of-the-art approaches. The comprehensive evaluation framework, incorporating Matthews Correlation Coefficient (MCC) and Cohen’s Kappa (CK), provides robust assessment for imbalanced classification scenarios. Results reveal that contextual embeddings consistently outperform traditional frequency-based methods, with BERT achieving perfect precision of 100% in baseline configurations. The study establishes strategic deployment guidelines: BERT configurations for maximum accuracy scenarios, Word2Vec approaches for balanced performance–efficiency requirements, and traditional methods for resource-constrained environments. Cross-linguistic validation confirms the universality of the approach, demonstrating only a 3.25% performance degradation in multilingual contexts. This research advances both theoretical understanding of imbalanced text classification and practical implementation of robust SMS spam detection systems, providing a methodological foundation applicable to broader cybersecurity and natural language processing challenges.

Similar Papers
  • Preprint Article
  • Citations1

Fusion-Based Hybrid Model for SMS Spam Detection Integrating Local, Sequential, and Contextual Features

  • Jan 23, 2025
  • Research Square
  • Hussein Al-Kaabi +4
  • Research Article

Comparative Study of Random Forest and Ordinal Regression in Concept Map Quality Assessment: The Role of TF-IDF, BERT, and SMOTE-based Balancing

  • Dec 21, 2025
  • ILKOM Jurnal Ilmiah
  • Nurul Rismayanti +3
  • Research Article
  • Citations1

Arabic text diacritization using transformers: a comparative study

  • Feb 01, 2025
  • IAES International Journal of Artificial Intelligence (IJ-AI)
  • Iman Zubeiri +2
  • Research Article
  • Citations20

BERT-based Transfer Learning in Sentence-level Anatomic Classification of Free-Text Radiology Reports.

  • Feb 15, 2023
  • Radiology: Artificial Intelligence
  • Daiki Nishigaki +7
  • Research Article

A Cost-Sensitive Hybrid Model of ALBERT Model and Convolutional Neural Network for Personality Classification

  • Apr 28, 2025
  • CommIT (Communication and Information Technology) Journal
  • Rilo Chandra Pradana +1
  • Research Article
  • Citations15

A Comparison of BiLSTM, BERT, and Ensemble Method for Emotion Recognition on Indonesian Product Reviews

  • Jan 01, 2024
  • Procedia Computer Science
  • Rio Pramana +3
  • PDF
  • Research Article
  • Citations18

Bidirectional encoders to state-of-the-art: a review of BERT and its transformative impact on natural language processing

  • Mar 02, 2024
  • Информатика. Экономика. Управление - Informatics. Economics. Management
  • Rajesh Gupta
  • Research Article
  • Citations4

Dilated convolution for enhanced extractive summarization: A GAN-based approach with BERT word embedding

  • Feb 14, 2024
  • Journal of Intelligent & Fuzzy Systems
  • Huimin Wu
  • Abstract
  • Citations5

Bert model fine-tuning for text classification in knee OA radiology reports

  • Apr 01, 2020
  • Osteoarthritis and Cartilage
  • L Chen +5
  • Research Article
  • Citations7

Short text automatic scoring system based on BERT-BiLSTM model

  • May 01, 2022
  • Journal of Shenzhen University Science and Engineering
  • Linzhong Xia +5
  • Research Article
  • Citations4

Analysis of Short Texts Using Intelligent Clustering Methods

  • May 19, 2025
  • Algorithms
  • Jamalbek Tussupov +6
  • Research Article

METAHEURISTIC-DRIVEN HYPERPARAMETER OPTIMIZATION FOR BERT IN SENTIMENT ANALYSIS

  • Oct 30, 2025
  • Archives for Technical Sciences
  • Alaa A El-Demerdash +1
  • Research Article
  • Citations1

Intelligent emotion sensing using BERT BiLSTM and generative AI for proactive customer care

  • Oct 01, 2025
  • Scientific Reports
  • Sandra Karunya G +1
  • Research Article
  • Citations19

Contextual classification of clinical records with bidirectional long short‐term memory (Bi‐LSTM) and bidirectional encoder representations from transformers (BERT) model

  • Aug 01, 2024
  • Computational Intelligence
  • Jaya Zalte +1
  • Conference Article
  • Citations9

Indonesian Sentiment Analysis Model from Social Media by Stacking BERT and BI-LSTM

  • Sep 07, 2022
  • Andry Chowanda +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.