Evaluation - task1-intertass-ST4-PE
1428 tweets in qrel, 1428 tweets in run.

Accuracy: 0.506

Confusion matrix
Real	Pred.	#
N	P	63
N	NONE	39
N	N	306
N	NEU	64
NEU	N	131
NEU	NONE	73
NEU	P	96
NEU	NEU	67
NONE	NEU	19
NONE	N	48
NONE	NONE	44
NONE	P	48
P	N	68
P	NEU	39
P	P	305
P	NONE	18

Category evaluation
Cat	P	R	F1
N	0.553	0.648	0.597
NEU	0.354	0.183	0.241
NONE	0.253	0.277	0.264
P	0.596	0.709	0.648

Macro-Precision: 0.439
Macro-Recall: 0.454
Macro-F1: 0.447