[Retracted] Network Public Opinion Risk Prediction and Judgment Based on Deep Learning: A Model of Text Sentiment Analysis

Table 6

Model parameters.

Parameter	BERT-CNN	BERT-Bi-LSTM	BCBL
Word vector dimension	768	768	768
Convolutional kernel size	[3–5]		[3, 4]
Number of filters	256		256
LSTM hidden size		64	64
Dropout	0.5	0.5	0.5
Epoch	10	10	10
Batch	24	24	24