Research Article
Multifeature Interactive Fusion Model for Aspect-Based Sentiment Analysis
Table 2
The performance of different methods.
| | Method | Restaurant (%) | Laptop (%) | Twitter (%) |
| | Majority | 53.50 | 65.00 | 50.00 | | LSTM | 74.30 | 66.50 | 66.50 | | TD-LSTM | 75.60 | 68.10 | 70.80 | | AE-LSTM | 76.60 | 68.90 | — | | ATAE-LSTM | 77.20 | 68.70 | — | | IAN | 78.60 | 72.10 | — | | IAD-ABSA | 79.0 | 72.5 | — | | PRET_MULT | 79.11 | 71.15 | — | | GCAE | 79.67 | 69.14 | — | | MF-ABSA | 80.64 | 74.69 | 70.0 | | MFIF-ABSA | 80.35 | 75.34 | 71.90 |
|
|
