Table 5.

Classification results of DWT-based feature extraction with/without preference indices and the valence index (V) and different classifiers: KNN, RF, SVM, and DNN using various activation functions in the DNN: hinge, and cross-entropy (categorical and binary) functions.

Classifiers	DNN									SVM			RF			KNN
	Hinge cross			Binary cross			Categorical cross
Preference indices	No	V	All	No	V	All	No	V	All	No	V	All	No	V	All	No	V	All
Accuracy	77	82	83	76	75	80	72	79	80	76	76	81	78	79	87	70	73	73
Recall	77	82	83	76	75	80	72	79	80	76	76	81	78	79	87	70	73	73
Precision	77	82	83	76	75	80	73	79	80	76	76	81	78	79	87	71	73	73