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

Accuracy: 0.593

Confusion matrix
Real	Pred.	#
N	N	534
N	NEU	73
N	P	89
N	NONE	71
NEU	NEU	46
NEU	N	82
NEU	P	60
NEU	NONE	28
NONE	NONE	89
NONE	P	86
NONE	N	76
NONE	NEU	23
P	NONE	46
P	N	97
P	P	457
P	NEU	42

Category evaluation
Cat	P	R	F1
N	0.677	0.696	0.686
NEU	0.250	0.213	0.230
NONE	0.380	0.325	0.350
P	0.660	0.712	0.685

Macro-Precision: 0.492
Macro-Recall: 0.486
Macro-F1: 0.489