Research Article
Bullet Subtitle Sentiment Classification Based on Affective Computing and Ensemble Learning
Table 6
Algorithm comparison results.
| Algorithm | Class | Accuracy | Precision | Recall | |
| Naive Bayes | | 0.937 | 0.900 | 0.963 | 0.930 | | 0.952 | 0.939 | 0.945 | TF-IDF + SVM | | 0.781 | 0.878 | 0.740 | 0.803 | | 0.675 | 0.871 | 0.761 | AT-LSTM | | 0.918 | 0.962 | 0.913 | 0.937 | | 0.845 | 0.929 | 0.885 | ATT-GRU | | 0.934 | 0.933 | 0.961 | 0.947 | | 0.936 | 0.893 | 0.927 | TextCNN | | 0.916 | 0.901 | 0.913 | 0.907 | | 0.944 | 0.910 | 0.927 | AdaBoost | | 0.937 | 0.924 | 0.945 | 0.934 | | 0.958 | 0.923 | 0.940 | RF | | 0.938 | 0.914 | 0.944 | 0.929 | | 0.940 | 0.955 | 0.947 | BSSCM | | 0.946 | 0.909 | 0.963 | 0.935 | | 0.958 | 0.954 | 0.956 |
|
|