Table 12. Machine learning algorithms with one hot encoding, BoW and without PCA using Python.

Race Group	Sample Size	Classification Accuracy (%)
		BoW-SVM	BoW-RF	BoW-LDA	BoW-QDA
AFRICAN	90	73.91	73.91	82.4	83.3
ASIAN	90	100	100	82.4	53.6
CAUCASIAN	90	100	100	100	100
Micro-accuracy		93.97	93.97	90.94	81.64
Macro-accuracy		91.30	91.30	88.27	78.97