A hybrid deep learning framework for fake news detection using LSTM-CGPNN and metaheuristic optimization.

The improvements over traditional approaches like CNN and Decision Tree-Random Forest (DT-RF) are highly significant ( p < 0.01), while comparisons with more advanced models like transformer-based architectures (BERT, RoBERTa, DeBERTa) and Graph Neural Networks (GNN) also show statistically significant improvements ( p < 0.05).

also in 132,142 other papers