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

Accuracy: 0.652

Confusion matrix
Real	Pred.	#
N	N	574
N	P	84
N	NONE	33
N	NEU	76
NEU	P	65
NEU	N	76
NEU	NEU	56
NEU	NONE	19
NONE	NEU	34
NONE	NONE	101
NONE	P	70
NONE	N	69
P	P	508
P	N	56
P	NEU	49
P	NONE	29

Category evaluation
Cat	P	R	F1
N	0.741	0.748	0.744
NEU	0.260	0.259	0.260
NONE	0.555	0.369	0.443
P	0.699	0.791	0.742

Macro-Precision: 0.564
Macro-Recall: 0.542
Macro-F1: 0.553