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

Accuracy: 0.572

Confusion matrix
Real	Pred.	#
N	P	132
N	N	581
N	NEU	19
N	NONE	35
NEU	P	79
NEU	N	109
NEU	NONE	18
NEU	NEU	10
NONE	P	106
NONE	NONE	47
NONE	NEU	13
NONE	N	108
P	N	159
P	P	449
P	NEU	14
P	NONE	20

Category evaluation
Cat	P	R	F1
N	0.607	0.757	0.674
NEU	0.179	0.046	0.074
NONE	0.392	0.172	0.239
P	0.586	0.699	0.638

Macro-Precision: 0.441
Macro-Recall: 0.419
Macro-F1: 0.429