Table 6 Detailed cross-validation results for STRATEGY 1 and the HerBERT model.

From: Analysis of the retraining strategies for multi-label text message classification in call/contact center systems

k

Training data

Testing data

Accuracy

Emotica

Accuracy

Emotica

[%]

[%]

[%]

[%]

1

99.73

98.40

93.60

78.20

2

99.68

98.11

94.17

79.59

3

99.56

97.38

93.78

79.59

Average

99.62

97.96

93.85

79.13

SD

0.06

0.43

0.24

0.66

  1. Significant values are in bold.
Back to article page