Table 10 Results of Word2Vec-based models on SMP2020-EWECT dataset.
From: A novel approach for multiclass sentiment analysis on Chinese social media with ERNIE-MCBMA
Models | Acc (%) | F1 (%) |
|---|---|---|
TextCNN | 70.00 | 70.15 |
TextRNN | 66.00 | 65.60 |
TextRCNN | 69.26 | 68.77 |
TextRNN_Att | 68.58 | 68.76 |
FastText | 67.52 | 67.45 |
Transformer | 66.78 | 67.16 |
Word2Vec-MCBMA | 70.54 | 69.74 |
