Skip to main content

Advertisement

Table 5 Performance comparison of the CNN model with other algorithms. SVM: Support Vector Machine; ET: Extra Trees; RF: Random Forest; LR: Logistics Regression; Bi-LSTM: Bi-directional Long Short-Term Memory. Bold number denotes the largest number in that row

From: Extracting psychiatric stressors for suicide from social media using deep learning

   CNN SVM ET RF LR Bi-LSTM
Precision Positive 0.78 0.7 0.69 0.69 0.7 0.73
Negative 0.69 0.72 0.58 0.5 0.67 0.65
Recall Positive 0.88 0.96 0.94 0.88 0.94 0.9
Negative 0.51 0.21 0.17 0.24 0.23 0.37
F-1 measure Positive 0.83 0.81 0.79 0.77 0.8 0.81
Negative 0.59 0.33 0.27 0.33 0.34 0.47
Accuracy 0.74 0.703 0.689 0.665 0.697 0.72