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

Accuracy: 0.612

Confusion matrix
Real	Pred.	#
N	N	587
N	P	91
N	NONE	34
N	NEU	55
NEU	P	57
NEU	N	107
NEU	NONE	18
NEU	NEU	34
NONE	NONE	94
NONE	P	75
NONE	N	75
NONE	NEU	30
P	NONE	36
P	N	117
P	P	448
P	NEU	41

Category evaluation
Cat	P	R	F1
N	0.663	0.765	0.710
NEU	0.213	0.157	0.181
NONE	0.516	0.343	0.412
P	0.668	0.698	0.682

Macro-Precision: 0.515
Macro-Recall: 0.491
Macro-F1: 0.503