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

Accuracy: 0.571

Confusion matrix
Real	Pred.	#
N	P	113
N	N	577
N	NEU	33
N	NONE	44
NEU	P	74
NEU	N	106
NEU	NEU	15
NEU	NONE	21
NONE	NONE	58
NONE	P	101
NONE	N	97
NONE	NEU	18
P	N	151
P	P	435
P	NEU	31
P	NONE	25

Category evaluation
Cat	P	R	F1
N	0.620	0.752	0.680
NEU	0.155	0.069	0.096
NONE	0.392	0.212	0.275
P	0.602	0.678	0.637

Macro-Precision: 0.442
Macro-Recall: 0.428
Macro-F1: 0.435