Skip to main content

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)

From: Automated doubt identification from informal reflections through hybrid sentic patterns and machine learning approach

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