Evaluation - task1-intertass-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.598

Confusion matrix
Real	Pred.	#
N	N	591
N	P	98
N	NONE	47
N	NEU	31
NEU	P	72
NEU	N	102
NEU	NEU	16
NEU	NONE	26
NONE	N	95
NONE	NONE	76
NONE	P	87
NONE	NEU	16
P	P	452
P	N	120
P	NEU	26
P	NONE	44

Category evaluation
Cat	P	R	F1
N	0.651	0.771	0.706
NEU	0.180	0.074	0.105
NONE	0.394	0.277	0.325
P	0.638	0.704	0.669

Macro-Precision: 0.465
Macro-Recall: 0.457
Macro-F1: 0.461