Skip to main content

Table 3 The performance of different \(\alpha\) parameter in the datasets

From: A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data

Model

Amazon Reviews

Chrome Reviews

\(\alpha = 0.25\)

\(\alpha = 0.5\)

\(\alpha = 0.75\)

\(\alpha = 0.25\)

\(\alpha = 0.5\)

\(\alpha = 0.75\)

Bert-Focal Loss \(Accuracy(\%)\)

91.85

91.23

92.76

92.60

92.19

93.35