Table 3. Metrics accuracy (Benchmark techniques VS MLEn).

Methods/Datasets	Automobiles (%)	Birds (%)	Emotions (%)	Hotel (%)	Medical (%)	Movies (%)	News (%)	Proteins (%)
DenseNet-EHO	0.89	0.96	0.95	0.93	0.97	0.92	0.93	0.99
BERT [52]	0.83	0.9	0.73	0.87	0.91	0.81	0.86	0.94
ML-RBF [30]	0.76	0.85	0.67	0.81	0.85	0.74	0.79	0.9
RAKEL [9]	0.77	0.86	0.68	0.82	0.86	0.76	0.81	0.91
RCC [31]	0.73	0.83	0.65	0.79	0.83	0.71	0.76	0.88
CNN [5]	0.79	0.88	0.7	0.84	0.88	0.78	0.83	0.92
NB [6]	0.72	0.82	0.63	0.77	0.82	0.69	0.75	0.87
LSTM [32]	0.81	0.88	0.72	0.85	0.89	0.8	0.84	0.92
ResNet [14]	0.83	0.9	0.73	0.87	0.91	0.81	0.86	0.94
CapsNet [33]	0.82	0.89	0.72	0.86	0.9	0.8	0.85	0.93
GRU [51]	0.78	0.75	0.79	0.77	0.8	0.78	0.75	0.79