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

Accuracy: 0.628

Confusion matrix
Real	Pred.	#
N	N	528
N	P	166
N	NONE	27
N	NEU	46
NEU	NEU	44
NEU	N	67
NEU	P	90
NEU	NONE	15
NONE	NONE	113
NONE	P	94
NONE	N	49
NONE	NEU	18
P	NONE	34
P	P	507
P	NEU	28
P	N	73

Category evaluation
Cat	P	R	F1
N	0.736	0.688	0.712
NEU	0.324	0.204	0.250
NONE	0.598	0.412	0.488
P	0.592	0.790	0.676

Macro-Precision: 0.562
Macro-Recall: 0.524
Macro-F1: 0.542