Manual validation metrics of 100 sample mappings for the semantic embedding method (SBERT) across four UK OC systems, where two annotators participated
| Dataset | Precision | Recall | F1 | Accuracy | Agreement | Kappa |
|---|---|---|---|---|---|---|
| SOC-ISCO | 0.88 | 1.00 | 0.94 | 0.88 | 76% | 0.23 |
| Scotland-N.Ireland | 0.73 | 1.00 | 0.84 | 0.73 | 79% | 0.54 |
| Scotland-Wales | 0.83 | 1.00 | 0.91 | 0.83 | 88% | 0.63 |
| Scotland-England | 0.98 | 1.00 | 0.99 | 0.98 | 90% | 0.67 |
| Dataset | Precision | Recall | F1 | Accuracy | Agreement | Kappa |
|---|---|---|---|---|---|---|
| SOC-ISCO | 0.88 | 1.00 | 0.94 | 0.88 | 76% | 0.23 |
| Scotland-N.Ireland | 0.73 | 1.00 | 0.84 | 0.73 | 79% | 0.54 |
| Scotland-Wales | 0.83 | 1.00 | 0.91 | 0.83 | 88% | 0.63 |
| Scotland-England | 0.98 | 1.00 | 0.99 | 0.98 | 90% | 0.67 |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.