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

Accuracy: 0.550

Confusion matrix
Real	Pred.	#
N	P	149
N	N	615
N	NONE	3
NEU	N	147
NEU	P	66
NEU	NEU	1
NEU	NONE	2
NONE	N	185
NONE	P	85
NONE	NONE	4
P	P	424
P	N	214
P	NONE	4

Category evaluation
Cat	P	R	F1
N	0.530	0.802	0.638
NEU	1.000	0.005	0.009
NONE	0.308	0.015	0.028
P	0.586	0.660	0.621

Macro-Precision: 0.606
Macro-Recall: 0.370
Macro-F1: 0.460