Table 4 Experimental performance of suicide-related tweets classification, using the CNN based algorithm and word embedding features of different dimensions. Bold number denotes the largest number in that row
From: Extracting psychiatric stressors for suicide from social media using deep learning
|  |  | D = 50 | D = 100 | D = 200 |
|---|---|---|---|---|
Precision | Positive | 0.78 | 0.76 | 0.79 |
Negative | 0.69 | 0.70 | 0.65 | |
Recall | Positive | 0.88 | 0.90 | 0.84 |
Negative | 0.51 | 0.45 | 0.56 | |
F-1 measure | Positive | 0.83 | 0.82 | 0.81 |
Negative | 0.59 | 0.55 | 0.60 |