Table 5 Quality of machine learning suggestions: Precision/recall of the machine learning text highlights with regard to the users’ final edits (calculated for each bias assessment which used machine learning assistance, and averaged)
Overall (n = 328) | RSG (n = 82) | AC (n = 82) | BPP (n = 82) | BOA (n = 82) | |
|---|---|---|---|---|---|
Recall (SD) | 0.90 (0.14) | 0.91 (0.18) | 0.92 (0.17) | 0.90 (0.19) | 0.91 (0.21) |
Precision (SD) | 0.87 (0.21) | 0.91 (0.21) | 0.88 (0.24) | 0.87 (0.25) | 0.87 (0.27) |