Table 5 Parameter settings of the benchmark models.
From: A novel approach for multiclass sentiment analysis on Chinese social media with ERNIE-MCBMA
Parameters | Values |
|---|---|
Dimension of word embedding vector | 300 |
Batchsize | 128 |
Number of convolutional kernels | 256 |
Epoch | 20 |
Learning_rate | 1e-3 |
Dropout | 0.5 |
