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

Accuracy: 0.514

Confusion matrix
Real	Pred.	#
N	NEU	169
N	NONE	140
N	N	415
N	P	43
NEU	NONE	65
NEU	N	56
NEU	NEU	78
NEU	P	17
NONE	NONE	147
NONE	N	30
NONE	NEU	60
NONE	P	37
P	P	336
P	N	51
P	NONE	98
P	NEU	157

Category evaluation
Cat	P	R	F1
N	0.752	0.541	0.629
NEU	0.168	0.361	0.229
NONE	0.327	0.536	0.406
P	0.776	0.523	0.625

Macro-Precision: 0.506
Macro-Recall: 0.491
Macro-F1: 0.498