Skip to main content

View full-text article in PMC

. 2025 Aug 14;9:e64536. doi: 10.2196/64536

Table 3.

Results of the baseline approach (n=463) in terms of accuracy, precision, sensitivity, specificity, and F1-score for each model.

Model		Accuracy (%)	Precision (%)	Sensitivity (%)	Specificity (%)	F₁-score (%)
Word_Tokenize
	BiLSTM^a	0.86	0.85	0.92	0.77	0.89
	GRU^b	0.86	0.86	0.91	0.79	0.89
	CNN^c	0.87	0.87	0.91	0.91	0.89
DeepCut
	BiLSTM	0.86	0.85	0.85	0.94	0.75
	GRU	0.85	0.84	0.83	0.91	0.84
	CNN	0.86	0.85	0.85	0.94	0.75
AttaCut
	BiLSTM	0.87	0.85	0.95	0.76	0.90
	GRU	0.86	0.86	0.92	0.79	0.89
	CNN	0.87	0.88	0.91	0.81	0.89

^aBiLSTM: bidirectional long short-term memory.

^bGRU: gated recurrent unit.

^cCNN: convolutional neural network.