Table 6 Results of various sentic patterns with performance metrics for both identifying doubt and overall doubt classification (P, R, F denotes Precision, Recall, and F1 score, respectively with P-y indicating Precision in identifying doubt or label ‘y’ during testing)
Pattern # | Sentic pattern + Doubt SPD algorithm | P-y | R-y | F-y | P | R | F |
|---|---|---|---|---|---|---|---|
1 | Questioning | 0.95 | 0.11 | 0.20 | 0.86 | 0.55 | 0.54 |
2 | Confirming | 0.67 | 0.08 | 0.15 | 0.72 | 0.53 | 0.51 |
3 | Affirming | 0.54 | 0.22 | 0.32 | 0.67 | 0.58 | 0.59 |
4 | Clarifying | 0.45 | 0.15 | 0.22 | 0.61 | 0.54 | 0.54 |
5 | Dissenting | 0.48 | 0.27 | 0.34 | 0.64 | 0.59 | 0.60 |
6 | 3+5 | 0.49 | 0.57 | 0.52 | 0.67 | 0.69 | 0.68 |
7 | 1+3+5 | 0.54 | 0.53 | 0.54 | 0.70 | 0.69 | 0.69 |
8 | 3+4+5 | 0.51 | 0.47 | 0.49 | 0.67 | 0.66 | 0.67 |
9 | 1+3+4+5 | 0.51 | 0.63 | 0.57 | 0.69 | 0.72 | 0.70 |
10 | 1+2+3+4+5 | 0.51 | 0.68 | 0.58 | 0.70 | 0.74 | 0.71 |