Skip to main content

Table 2 Average F1-macro scores with standard deviation by model architecture

From: AutoDiscern: rating the quality of online health information with hierarchical encoder attention-based neural networks

Model Architecture

Q4: References

Q5: Date

Q9: How Treatment Works

Random Forest

0.83 (4)

0.70 (6)

0.66 (10)

HE BERT

0.72 (14)

0.77 (3)

0.66 (13)

HE BioBERT

0.71 (13)

0.78 (5)

0.66 (11)

HEA BERT

0.86 (3)

0.77 (4)

0.68 (10)

HEA BioBERT

0.80 (7)

0.82 (6)

0.72 (10)

Model Architecture

Q10: Tt. Benefits

Q11: Tt. Risks

All Questions Avg

Random Forest

0.53 (15)

0.72 (4)

0.69

HE BERT

0.60 (11)

0.74 (4)

0.70

HE BioBERT

0.56 (11)

0.80 (4)

0.70

HEA BERT

0.66 (2)

0.76 (3)

0.75

HEA BioBERT

0.54 (9)

0.81 (5)

0.74