Research Article
An End-to-End Rumor Detection Model Based on Feature Aggregation
Table 5
Performance of proposed text content model (R: rumor; N: nonrumor).
| Method | Label | Accuracy | Precision | Recall | |
| GRU-2 | R | 0.910 | 0.876 | 0.956 | 0.914 | N | 0.952 | 0.864 | 0.906 |
| CAMI | R | 0.933 | 0.921 | 0.945 | 0.933 | N | 0.945 | 0.921 | 0.932 |
| RNN-Text | R | 0.915 | 0.916 | 0.918 | 0.917 | N | 0.914 | 0.912 | 0.913 |
| CNN-Text | R | 0.937 | 0.923 | 0.956 | 0.939 | N | 0.952 | 0.917 | 0.934 |
|
|