Scholarlink

<p>This paper introduces a method for fake accounts detection on social media through machine learning using several classification algorithms and sophisticated feature extraction. Preprocessing steps included dataset integration, feature normalization, entropy-based feature extraction, behavioral ratio computation, and class imbalance handling using SMOTE and SMOTEENN. Ensemble learning models, including LightGBM, CatBoost, XGBoost, and Logistic Regression, were trained on the training dataset and subsequently evaluated on the unseen testing dataset to assess their classification performance. Models were evaluated using accuracy, precision, recall, F1 score, and confusion matrices. SHAP explanation displayed the feature contributions. Experimental results demonstrated the effectiveness of the proposed approach, achieving the highest predictive accuracy of 99.71% and a balanced F1-score of 99.70%. These findings demonstrate excellent discriminative performance in distinguishing real accounts from the fake accounts and generated the following implications. Mixtures of feature selection, resampling strategies, and explainable AI can clearly enhance fake account detection. The proposed framework provides a scalable and effective solution for identifying fraudulent social media accounts and enhancing trust and security across online platforms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Explainable hybrid ensemble for fake account detection using DSM-FS and SMOTEENN

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月7日

查看全文
  • Zahraa Azhar Muhammad Shamki,
  • Ali Abdulkarem Habib Alrammahi,
  • Farah Abbas Obaid Sari,
  • Mustafa Noaman Kadhim,
  • Dhiah Al-Shammary,
  • Ayman Ibaida,
  • Assefa K. Teshome,
  • Khandakar Ahmed

摘要

This paper introduces a method for fake accounts detection on social media through machine learning using several classification algorithms and sophisticated feature extraction. Preprocessing steps included dataset integration, feature normalization, entropy-based feature extraction, behavioral ratio computation, and class imbalance handling using SMOTE and SMOTEENN. Ensemble learning models, including LightGBM, CatBoost, XGBoost, and Logistic Regression, were trained on the training dataset and subsequently evaluated on the unseen testing dataset to assess their classification performance. Models were evaluated using accuracy, precision, recall, F1 score, and confusion matrices. SHAP explanation displayed the feature contributions. Experimental results demonstrated the effectiveness of the proposed approach, achieving the highest predictive accuracy of 99.71% and a balanced F1-score of 99.70%. These findings demonstrate excellent discriminative performance in distinguishing real accounts from the fake accounts and generated the following implications. Mixtures of feature selection, resampling strategies, and explainable AI can clearly enhance fake account detection. The proposed framework provides a scalable and effective solution for identifying fraudulent social media accounts and enhancing trust and security across online platforms.