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

Accuracy: 0.595

Confusion matrix
Real	Pred.	#
N	N	589
N	P	99
N	NONE	49
N	NEU	30
NEU	P	75
NEU	N	102
NEU	NEU	14
NEU	NONE	25
NONE	N	96
NONE	NONE	75
NONE	P	87
NONE	NEU	16
P	P	451
P	N	119
P	NEU	26
P	NONE	46

Category evaluation
Cat	P	R	F1
N	0.650	0.768	0.704
NEU	0.163	0.065	0.093
NONE	0.385	0.274	0.320
P	0.633	0.702	0.666

Macro-Precision: 0.458
Macro-Recall: 0.452
Macro-F1: 0.455