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

Accuracy: 0.668

Confusion matrix
Real	Pred.	#
N	N	592
N	NEU	62
N	P	81
N	NONE	32
NEU	P	65
NEU	N	76
NEU	NEU	50
NEU	NONE	25
NONE	NEU	30
NONE	NONE	101
NONE	P	73
NONE	N	70
P	P	526
P	N	56
P	NEU	32
P	NONE	28

Category evaluation
Cat	P	R	F1
N	0.746	0.772	0.758
NEU	0.287	0.231	0.256
NONE	0.543	0.369	0.439
P	0.706	0.819	0.758

Macro-Precision: 0.570
Macro-Recall: 0.548
Macro-F1: 0.559