Table 2.
10-fold cross validation performance on the baseline model and hierarchical classification model. (F: F-1 score; P: precision; R: recall; for the categories that do not indicate the metric, F-1 score are used)
Classification Model | Plain Classification (Baseline model) | Hierarchical Classification | |
---|---|---|---|
Micro-averaging | F | 0.6732 | 0.7208 |
Macro-averaging | P | 0.4455 | 0.5402 |
R | 0.3574 | 0.4386 | |
F | 0.3967 | 0.4841 | |
Unrelated | 0.8044 | 0.8599 | |
Neutral | 0.5792 | 0.6181 | |
Positive | 0.6528 | 0.7021 | |
NegSafety | 0.7006 | 0.7277 | |
NegEfficacy | 0 | 0.2593 | |
NegCost | 0 | 0 | |
NegResistant | 0 | 0 | |
NegOthers | 0.155 | 0.4645 |