Table 11 Hyperparameters setting for different deep learning algorithms.
From: Impact of ByteDance crisis communication strategies on different social media users
Algorithm | Hyperparameters setting | |||
|---|---|---|---|---|
LSTM | Hidden units=256 | Learning rate=0.001 | Epochs-20 | Regularization parameter=0.001 |
BERT | Learning rate=2e-5 | Batch size=16 | Maximum sequence length=256 | Iterations=10 |
ERNIE | Learning rate=2e-5 | Batch size=16 | Maximum sequence length=256 | Iterations=10 |
