Sentiment Classification of Educational Tourism Reviews Based on Parallel CNN and LSTM with Attention Mechanism

Table 4

Network parameters.

Network parameters	CNN	LSTM
Word embedding dimensions	256	256
Learning ratio	0.001	0.001
Kernel size	128	—
Convolution window size	2, 3	—
Hidden layers	—	256
Drop_out	0.5	0.5
Activation function	ReLU	ReLU