Evaluation - task1-intertass-CR
1233 tweets in qrel, 1233 tweets in run.

Accuracy: 0.509

Confusion matrix
Real	Pred.	#
N	N	413
N	P	63
N	NONE	15
NEU	N	102
NEU	P	55
NEU	NONE	7
NONE	N	142
NONE	P	76
NONE	NONE	5
NONE	NEU	1
P	N	131
P	P	209
P	NONE	13
P	NEU	1

Category evaluation
Cat	P	R	F1
N	0.524	0.841	0.646
NEU	0.000	0.000	0.000
NONE	0.125	0.022	0.038
P	0.519	0.590	0.552

Macro-Precision: 0.292
Macro-Recall: 0.363
Macro-F1: 0.324