Research Article
Detecting Fake Reviews with Generative Adversarial Networks for Mobile Social Networks
Table 4
Results on different learning rates.
| Learning rate | AUC | Precision | Recall | F1-score |
| 1 | 0.522 | 0.513 | 0.520 | 0.516 | 0.1 | 0.676 | 0.677 | 0.678 | 0.677 | 0.01 | 0.748 | 0.750 | 0.749 | 0.749 | 0.001 | 0.780 | 0.780 | 0.776 | 0.778 | 5e − 4 | 0.788 | 0.788 | 0.781 | 0.784 | 1e − 5 | 0.788 | 0.789 | 0.780 | 0.784 | Learning rate decay (from 1e − 3 to 1e − 5) | 0.787 | 0.785 | 0.783 | 0.784 | Adam | 0.792 | 0.788 | 0.790 | 0.789 | Adam + learning rate decay (from 1e − 3 to 1e − 5) | 0.795 | 0.796 | 0.800 | 0.798 |
|
|