Table 2 Activity codes by content analytic text mining approaches
From: Identifying work related injuries: comparison of methods for interrogating text fields
| Â | Work Activity code | Other Activity code | Â | ||
|---|---|---|---|---|---|
Content Analytic Text Mining Methods | n | % | n | % | Total |
Binary classification | Â | Â | Â | Â | Â |
   'Work SPV Tag' | 17,299 | 80.8 | 13,894 | 7.4 | 31,193 |
   Not 'Work SPV Tag' | 4,120 | 19.2 | 172,968 | 92.6 | 177,088 |
Adjusted probability classification | Â | Â | Â | Â | Â |
   Classified as 'Work Activity' | 16,424 | 76.7 | 8,699 | 4.7 | 25,123 |
   Classified as 'Other Activity' | 4,995 | 23.3 | 178,163 | 95.3 | 183,158 |
Total | 21,419 | 100 | 186,862 | 100 | 208,281 |