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

Accuracy: 0.510

Confusion matrix
Real	Pred.	#
N	N	388
N	P	302
N	NEU	77
NEU	P	120
NEU	N	67
NEU	NEU	29
NONE	P	186
NONE	N	76
NONE	NEU	12
P	P	552
P	N	78
P	NEU	12

Category evaluation
Cat	P	R	F1
N	0.637	0.506	0.564
NEU	0.223	0.134	0.168
NONE	0.000	0.000	0.000
P	0.476	0.860	0.613

Macro-Precision: 0.334
Macro-Recall: 0.375
Macro-F1: 0.353