A Weighted-Distance Ensemble Learning Method for Arabic Fake News Detection

Abstract

In the digital era, the rapid proliferation of fake news poses critical challenges to information credibility and public trust, particularly in Arabic news ecosystems where linguistic complexity and limited annotated resources exacerbate detection difficulties. This study proposes a framework for Arabic fake news detection based on a weighted-distance ensemble learning method (WDELM). The WDELM framework combines posterior-probability estimates from six heterogeneous base classifiers: extreme gradient boosting (XGBoost), LightGBM (LGBM), random forest (RF), adaptive boosting (AdaBoost), gradient boosting (GB), and logistic regression (LR). The classifier outputs are integrated through a distance-aware adaptive weighting strategy based on cosine distance in the prediction space. Unlike conventional ensemble techniques, the proposed framework employs normalised distance-aware adaptive weighting to adapt classifier contributions while preserving the probabilistic interpretation of the final ensemble output. Experiments were conducted on an Arabic fake news dataset comprising 2538 manually annotated instances. The model was evaluated using multiple performance metrics, including precision, recall, F1-score, Cohen’s kappa, ROC-AUC, and accuracy, together with explainability analyses. Using stratified ten-fold cross-validation, the proposed WDELM achieved a mean accuracy of 92.120±1.097% and a mean ROC-AUC of 97.125±0.686%. Analysis of the concatenated predictions generated across the ten outer-validation folds yielded an F1-score of 91.357% for the Fake class, an F1-score of 92.759% for the Real class, and a pooled macro-F1 score of 92.058%, indicating balanced classification performance across both classes. The results indicate that the proposed weighted-distance ensemble strategy provides improved empirical performance within the evaluated dataset and offers a transparent mechanism for combining heterogeneous classifiers. The framework is further assessed through statistical validation, error analysis, and explainability analysis, supporting its potential use as an auxiliary decision-support tool for Arabic fake news screening rather than as a fully automated replacement for professional fact-checking.