Multi-Rule Based Ensemble Feature Selection Model for Sarcasm Type Detection in Twitter

Table 4

Classification accuracy obtained by the proposed rough set approach.

Average accuracy (%)
	Correct	Incorrect
Total	98.81	1.19
Polite	95.98	4.02
Rude	96.2	3.8
Raging	99.79	0.21
Deadpan	86.61	13.39