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

Accuracy: 0.465

Confusion matrix
Real	Pred.	#
N	P	17
N	N	267
N	NEU	121
N	NONE	67
NEU	NEU	102
NEU	N	97
NEU	NONE	119
NEU	P	49
NONE	NONE	56
NONE	N	33
NONE	P	31
NONE	NEU	39
P	P	239
P	N	32
P	NEU	118
P	NONE	41

Category evaluation
Cat	P	R	F1
N	0.622	0.566	0.593
NEU	0.268	0.278	0.273
NONE	0.198	0.352	0.253
P	0.711	0.556	0.624

Macro-Precision: 0.450
Macro-Recall: 0.438
Macro-F1: 0.444