Skip to main content

Table 5 Performance of CNN-based models and LSTM-based models in Ablation Study

From: Neural side effect discovery from user credibility and experience-assessed online health discussions

Systems Components Evaluation Metrics
  CW UE CA Pre. Rec. F1
LSTM-Vanilla     0.6173 0.407 0.4335
LSTM-WPE    0.6376 0.4344 0.4503
LSTM-WPEU   0.6064 0.5001 0.4896
LSTM-NEAT 0.6197 0.5134 0.5064
CNN-Vanilla     0.7214 0.5503 0.5637
CNN-WPE    0.7423 0.5799 0.5804
CNN-WPEU   0.6923 0.6350 0.5910
CNN-NEAT 0.7066 0.6431 0.6139
  1. In the Components column, CW, UE, CA denote Credibility Weights, User Expertise and Cluster Attention module components, respectively. In the Evaluation Metrics column, Pre., Rec. and F1 denote Precision, Recall, and F1 score