Table 3 Performance of the ANOVA F-test feature selection on the StockTwits dataset
From: Big Data: Deep Learning for financial sentiment analysis
Features | Accuracy | Precision | Recall | F-measure | AUC |
|---|---|---|---|---|---|
55,820 | 0.7088 | 0.7134 | 0.6980 | 0.7056 | 0.7088 |
40,000 | 0.7094 | 0.7130 | 0.7010 | 0.7070 | 0.7094 |
20,000 | 0.7091 | 0.7127 | 0.7007 | 0.7066 | 0.7091 |
4000 | 0.5274 | 0.5206 | 0.6946 | 0.5951 | 0.5274 |
2000 | 0.7045 | 0.7048 | 0.7038 | 0.7043 | 0.7045 |
400 | 0.6785 | 0.6638 | 0.7233 | 0.6923 | 0.6785 |
200 | 0.6611 | 0.6378 | 0.7457 | 0.6875 | 0.6611 |
50 | 0.0.6191 | 0.5863 | 0.8084 | 0.6797 | 0.6191 |