On the development of an information system for monitoring user opinion and its role for the public

Journal of Big Data

Table 9 The classification metrics for the undersampled Russian texts

Classifier	NB	SVM	LR	k-NN	DT	RF	XGBoost	Average
Accuracy	0.57	0.53	0.72	0.39	0.63	0.71	0.62	0.60
Precision-macro	0.66	0.55	0.72	0.60	0.65	0.72	0.62	0.65
Precision-micro	0.57	0.53	0.72	0.39	0.63	0.71	0.62	0.60
Precision-weighted	0.66	0.55	0.72	0.61	0.65	0.72	0.63	0.65
Recall-macro	0.57	0.54	0.72	0.40	0.63	0.72	0.63	0.60
Recall-micro	0.57	0.53	0.72	0.39	0.63	0.71	0.62	0.60
Recall-weighted	0.57	0.53	0.72	0.39	0.63	0.71	0.62	0.60
F1-score-macro	0.56	0.44	0.71	0.30	0.62	0.71	0.62	0.57
F1-score-micro	0.57	0.53	0.72	0.39	0.63	0.71	0.62	0.60
F1-score-weighted	0.56	0.44	0.71	0.30	0.62	0.71	0.61	0.56
Average	0.59	0.52	0.72	0.42	0.63	0.71	0.62