Skip to main content

Table 6 Precision (P), recall (R), and F1-measure (F) 10-fold cross validation results on training data

From: Personality-dependent content selection in natural language generation systems

 

Context info

Speaker ids

Personality info

Class

P

R

F

P

R

F

P

R

F

isYoung

0.56

0.50

0.52

0.34

0.60

0.48

0.50

0.66

0.58

Race

0.78

0.81

0.79

0.40

0.58

0.49

0.63

0.62

0.65

Emotion

0.68

0.57

0.62

0.55

0.82

0.64

0.70

0.83

0.73

Smile

0.70

0.65

0.69

0.38

0.64

0.50

0.58

0.65

0.60

Eyebrows

0.62

0.68

0.59

0.61

0.85

0.69

0.74

0.89

0.79

hair.colour

0.70

0.59

0.65

0.47

0.69

0.57

0.65

0.72

0.66

hair.length

0.69

0.79

0.72

0.52

0.78

0.59

0.66

0.75

0.67

Ponytail

0.86

0.98

0.87

0.81

0.89

0.83

0.89

0.91

0.89

eye.colour

0.68

0.76

0.72

0.60

0.82

0.67

0.78

0.89

0.81

Mean

0.70

0.70

0.69

0.52

0.74

0.61

0.68

0.77

0.71

  1. Best F1 results are highlighted