Table 2 Performance of the Chi-squared 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 | 0.4796 | 0.4851 | 0.6645 | 0.5608 | 0.4796 |
20,000 | 0.5018 | 0.5013 | 0.6879 | 0.5800 | 0.5018 |
4000 | 0.5274 | 0.5206 | 0.6946 | 0.5951 | 0.5274 |
2000 | 0.5221 | 0.5190 | 0.6036 | 0.5581 | 0.5221 |
400 | 0.5308 | 0.5278 | 0.5834 | 0.5542 | 0.5308 |
200 | 0.5333 | 0.5280 | 0.6284 | 0.5738 | 0.5333 |
50 | 0.5314 | 0.5232 | 0.7071 | 0.6014 | 0.5314 |