From: Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media
Model
Baseline Classifier
Optimized classifier
Metrics
Precision
Recall
F1 Score
Accuracy
First Dataset
87.5
84.6
86.0
91.6
89.1
86.6
87.9
92.7
Second Dataset
61.5
55.0
58.1
85.1
66.5
55.6
60.5
86.4