Table 4 Classification performance
From: Identifying tweets of personal health experience through word embedding and LSTM neural network
Classifier | Accuracy | Precision (PET) | Recall (PET) | F1 (PET) | ROC/AUC |
|---|---|---|---|---|---|
Logistic Regression | 0.637 | 0.356 | 0.471 | 0.405 | 0.598 |
Decision Tree | 0.602 | 0.329 | 0.442 | 0.357 | 0.547 |
KNN | 0.669 | 0.383 | 0.481 | 0.411 | 0.604 |
SVM | 0.635 | 0.339 | 0.478 | 0.393 | 0.580 |
BoW + Logistic Regr. | 0.757 | 0.498 | 0.567 | 0.530 | 0.698 |
Word Embedding + LSTM | 0.815 | 0.598 | 0.702 | 0.645 | 0.776 |