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

Accuracy: 0.625

Confusion matrix
Real	Pred.	#
N	N	523
N	NEU	94
N	P	86
N	NONE	64
NEU	NONE	29
NEU	N	69
NEU	NEU	68
NEU	P	50
NONE	NONE	142
NONE	N	52
NONE	P	50
NONE	NEU	30
P	P	453
P	NEU	62
P	N	75
P	NONE	52

Category evaluation
Cat	P	R	F1
N	0.727	0.682	0.704
NEU	0.268	0.315	0.289
NONE	0.495	0.518	0.506
P	0.709	0.706	0.707

Macro-Precision: 0.550
Macro-Recall: 0.555
Macro-F1: 0.552