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

Accuracy: 0.551

Confusion matrix
Real	Pred.	#
N	N	345
N	NEU	23
N	NONE	74
N	P	49
NEU	N	76
NEU	P	42
NEU	NEU	18
NEU	NONE	28
NONE	N	76
NONE	NONE	91
NONE	P	37
NONE	NEU	20
P	P	225
P	N	53
P	NEU	27
P	NONE	49

Category evaluation
Cat	P	R	F1
N	0.627	0.703	0.663
NEU	0.205	0.110	0.143
NONE	0.376	0.406	0.391
P	0.637	0.636	0.636

Macro-Precision: 0.461
Macro-Recall: 0.464
Macro-F1: 0.462