Step 5 · Review
Field validation
NLP predictions vs. human ground-truth annotations across 800 narratives.
Evaluated corpus size
800
Annotated narratives
Macro F1
0.88
Target ≥ 0.75
Cohen's κ
0.84
Substantial agreement
Accuracy
0.89
Exact match
Confusion matrix
| True ↓ / Pred → | FGM | Child marriage | Other harmful norm | No signal |
|---|---|---|---|---|
| FGM | 182 | 9 | 6 | 3 |
| Child marriage | 11 | 164 | 8 | 5 |
| Other harmful norm | 7 | 10 | 121 | 14 |
| No signal | 4 | 3 | 12 | 241 |
Per-class F1
FGM0.90
Child marriage0.88
Other harmful norm0.81
No signal0.92
Per-class report
| Class | Precision | Recall | F1 | Support |
|---|---|---|---|---|
| FGM | 0.89 | 0.91 | 0.90 | 200 |
| Child marriage | 0.88 | 0.87 | 0.88 | 188 |
| Other harmful norm | 0.82 | 0.80 | 0.81 | 152 |
| No signal | 0.92 | 0.93 | 0.92 | 260 |
| Macro avg | 0.88 | 0.88 | 0.88 | 800 |