Table 10 Impact of entity and concept knowledge on model performance for PHEME datasets
From: KAGN:knowledge-powered attention and graph convolutional networks for social media rumor detection
Variants | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|
PTE | 0.8125 | 0.8056 | 0.8125 | 0.8052 |
PTE + KGE/E | 0.7813 | 0.7886 | 0.7813 | 0.7457 |
PTE + KGE/C | 0.7917 | 0.8061 | 0.7917 | 0.7578 |
PTE + KGE | 0.8281 | 0.8228 | 0.8281 | 0.8208 |
PTE + KAE/E | 0.8333 | 0.8298 | 0.8333 | 0.8241 |
PTE + KAE/C | 0.8490 | 0.8469 | 0.8489 | 0.8477 |
PTE + KAE | 0.8594 | 0.8594 | 0.8594 | 0.8593 |