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

Accuracy: 0.574

Confusion matrix
Real	Pred.	#
N	N	558
N	NONE	75
N	P	90
N	NEU	44
NEU	NONE	44
NEU	N	98
NEU	P	59
NEU	NEU	15
NONE	NONE	91
NONE	N	88
NONE	P	72
NONE	NEU	23
P	P	426
P	N	117
P	NONE	76
P	NEU	23

Category evaluation
Cat	P	R	F1
N	0.648	0.728	0.686
NEU	0.143	0.069	0.093
NONE	0.318	0.332	0.325
P	0.658	0.664	0.661

Macro-Precision: 0.442
Macro-Recall: 0.448
Macro-F1: 0.445