Table 9 Comparison evaluation of the EDTIWVR-MDNN method with other existing techniques under the TER dataset40,41.

From: Integration of corpus linguistics and deep learning techniques for enhanced semantic-driven emotion detection on textual data

TER

Methods

\(\:{A}{c}{c}{{u}}_{{y}}\)

\(\:{P}{r}{e}{{c}}_{{n}}\)

\(\:{R}{e}{c}{{a}}_{{l}}\)

\(\:{{F}1}_{{s}{c}{o}{r}{e}}\)

SVM

78.97

81.45

78.36

79.67

RF

76.25

79.42

75.66

77.02

NB

68.94

61.75

51.41

49.61

DT

69.42

72.48

69.70

70.94

GRU

78.02

71.19

73.91

72.35

CNN

79.32

77.30

75.21

74.10

EDTIWVR-MDNN

97.26

96.68

96.20

95.94

Back to article page