Table 4 Accuracy performance among proposed and existing SA schemes.

From: Optimized hierarchical CLSTM model for sentiment classification of tweets using boosted killer whale predation strategy

Emotion classes

Proposed OTCNLSTM

BERT-CNN

LSTM

CNN

Anger

90.4

84.5

80.1

78.14

Happy

90.2

84

79.8

78.1

Neutral

90

84.2

80.05

78

Sad

90.2

84.3

81

78.1

Back to article page