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

Accuracy: 0.583

Confusion matrix
Real	Pred.	#
N	N	556
N	P	87
N	NEU	14
N	NONE	110
NEU	P	66
NEU	N	94
NEU	NONE	50
NEU	NEU	6
NONE	NONE	122
NONE	P	62
NONE	N	87
NONE	NEU	3
P	P	424
P	N	104
P	NONE	104
P	NEU	10

Category evaluation
Cat	P	R	F1
N	0.661	0.725	0.692
NEU	0.182	0.028	0.048
NONE	0.316	0.445	0.370
P	0.664	0.660	0.662

Macro-Precision: 0.456
Macro-Recall: 0.465
Macro-F1: 0.460