Skip to main content

Table 2 Performances of deep learning models in terms of class-specific recall, precision and F1-scores, and overall accuracy

From: Text classification models for the automatic detection of nonmedical prescription medication use from social media

Classification algorithm

Precision

Recall

F1-score

Accuracy (%)

A

C

M

U

A

C

M

U

A

C

M

U

CNN (Twitter-GloVe-embedding)

0.47

0.65

0.75

0.76

0.39

0.61

0.82

0.69

0.43

0.63

0.79

0.72

69.03

Char-CNN

0.36

0.63

0.72

0.57

0.32

0.50

0.81

0.58

0.34

0.56

0.76

0.58

64.04

BiLSTM Twitter-GloVe-embedding

0.44

0.70

0.77

0.76

0.45

0.60

0.82

0.76

0.45

0.65

0.80

0.76

70.01

  1. Best F1-score on the A class is shown in bold