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

Accuracy: 0.600

Confusion matrix
Real	Pred.	#
N	N	561
N	NONE	110
N	P	88
N	NEU	8
NEU	P	51
NEU	N	110
NEU	NONE	54
NEU	NEU	1
NONE	NONE	169
NONE	N	59
NONE	P	46
P	P	409
P	NONE	100
P	N	125
P	NEU	8

Category evaluation
Cat	P	R	F1
N	0.656	0.731	0.692
NEU	0.059	0.005	0.009
NONE	0.390	0.617	0.478
P	0.689	0.637	0.662

Macro-Precision: 0.448
Macro-Recall: 0.497
Macro-F1: 0.472