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

Accuracy: 0.578

Confusion matrix
Real	Pred.	#
N	P	122
N	N	588
N	NEU	19
N	NONE	38
NEU	P	83
NEU	N	108
NEU	NONE	15
NEU	NEU	10
NONE	NONE	53
NONE	P	107
NONE	N	102
NONE	NEU	12
P	N	154
P	P	447
P	NEU	19
P	NONE	22

Category evaluation
Cat	P	R	F1
N	0.618	0.767	0.684
NEU	0.167	0.046	0.072
NONE	0.414	0.193	0.264
P	0.589	0.696	0.638

Macro-Precision: 0.447
Macro-Recall: 0.426
Macro-F1: 0.436