TABLE 23. The Performance of Cross-Validation for Deep Neural Networks (Gossip Cop Dataset).

DL models	Measure Performance Methods
	Accuracy	Precision	Recall	F1-score
Modified LSTM one layer	82.5± 1.27	81.52± 4.12	79.37± 5.84	80.0± 1.74
Modified LSTM two layers	75.18± 0.86	74.78± 2.79	68.09± 5.16	70.92± 1.88
Modified LSTM three layers	75.22± 0.69	74.32± 2.59	68.78± 5.01	71.07± 1.77
Modified GRU one layer	74.81± 0.87	73.45± 2.93	69.66± 6.6	70.98± 2.49
Modified GRU two layers	86.05± 1.83	82.97± 6.84	75.66± 6.06	78.32± 4.81
Modified GRU three layers	79.74± 0.95	78.68± 3.63	75.95± 5.28	76.88± 1.43