Evaluation - task1-intertass-ST4-CR
1233 tweets in qrel, 1233 tweets in run.

Accuracy: 0.542

Confusion matrix
Real	Pred.	#
N	N	333
N	NONE	114
N	P	37
N	NEU	7
NEU	N	75
NEU	P	33
NEU	NONE	49
NEU	NEU	7
NONE	N	68
NONE	NONE	124
NONE	P	31
NONE	NEU	1
P	P	204
P	N	52
P	NONE	91
P	NEU	7

Category evaluation
Cat	P	R	F1
N	0.631	0.678	0.654
NEU	0.318	0.043	0.075
NONE	0.328	0.554	0.412
P	0.669	0.576	0.619

Macro-Precision: 0.486
Macro-Recall: 0.463
Macro-F1: 0.474