Table 2 The performance comparisions of different models on the microblogs.
From: Emoji multimodal microblog sentiment analysis based on mutual attention mechanism
Models | \(P_{Macro}\) (%) | \(R_{Macro}\) (%) | \(F1_{Macro}\) (%) | Acc (%) |
|---|---|---|---|---|
SVM | 64.27 | 62.56 | 63.41 | 70.13 |
Bi-LSTM(word) | 66.87 | 65.94 | 66.40 | 75.54 |
Bi-LSTM(word+emoji) | 77.30 | 73.92 | 75.57 | 83.91 |
EA-Bi-LSTM | 81.61 | 75.82 | 78.61 | 85.35 |
ECN | 82.65 | 75.69 | 79.02 | 86.62 |
MAM-EMMSA | 83.85 | 77.26 | 80.42 | 87.95 |
