Skip to main content

Table 5 Experimental comparison results of ERNIE with other word embedding models

From: Research on sentiment analysis method of opinion mining based on multi-model fusion transfer learning

Method

Accuracy

Precision

Recall

F1-measure

Word2Vec

0.898

0.891

0.885

0.888

BERT

0.916

0.908

0.902

0.905

TETBA

0.937

0.930

0.921

0.925