Table 8 Best impact of the KG for the influential paper classification task (WHO = World Health Organization (COVID-19 Global literature on coronavirus disease); LR = Logistic Regression; RF = Random Forest; P = Precision; R = Recall; F1 = F1 score; A = Accuracy; MA = Macro average; WA = Weighted average; D_U_B = DBpedia Unqualified Relation with Bag-of-words; D_D_B = DBpedia Direct Type with Bag-of-words
Data | ML | Repr. | P | R | F1 | A | MA | WA | |
|---|---|---|---|---|---|---|---|---|---|
WHO-Un | RF | BOW | High | 0.96 | 0.58 | 0.72 | 0.78 | 0.77 | 0.77 |
Low | 0.70 | 0.98 | 0.81 | ||||||
WHO-Un | RF | D_U_B | High | 0.97 | 0.58 | 0.72 | 0.78 | 0.77 | 0.77 |
Low | 0.70 | 0.98 | 0.82 | ||||||
WHO-Un | RF | D_D_B | High | 0.96 | 0.58 | 0.72 | 0.78 | 0.77 | 0.77 |
Low | 0.70 | 0.98 | 0.81 | ||||||
WHO-4 | LR | BOW | High | 0.54 | 0.54 | 0.54 | 0.51 | 0.51 | 0.51 |
Low | 0.51 | 0.44 | 0.47 | ||||||
WHO-4 | LR | D_U_B | High | 0.59 | 0.65 | 0.62 | 0.66 | 0.66 | 0.65 |
Low | 0.62 | 0.50 | 0.54 | ||||||
WHO-4 | LR | D_D_B | High | 0.54 | 0.58 | 0.56 | 0.62 | 0.61 | 0.61 |
Low | 0.50 | 0.45 | 0.47 | ||||||
WHO-30 | LR | BOW | High | 0.62 | 0.65 | 0.63 | 0.64 | 0.64 | 0.64 |
Low | 0.66 | 0.65 | 0.64 | ||||||
WHO-30 | LR | D_U_B | High | 0.70 | 0.80 | 0.73 | 0.71 | 0.69 | 0.69 |
Low | 0.66 | 0.63 | 0.64 | ||||||
WHO-30 | LR | D_D_B | High | 0.65 | 0.75 | 0.69 | 0.67 | 0.65 | 0.66 |
Low | 0.70 | 0.59 | 0.62 |