Evaluation - task1-intertass-ST4-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.498

Confusion matrix
Real	Pred.	#
N	N	366
N	P	132
N	NONE	175
N	NEU	94
NEU	P	64
NEU	N	52
NEU	NONE	62
NEU	NEU	38
NONE	NONE	119
NONE	P	82
NONE	NEU	33
NONE	N	40
P	P	423
P	NONE	113
P	N	41
P	NEU	65

Category evaluation
Cat	P	R	F1
N	0.733	0.477	0.578
NEU	0.165	0.176	0.170
NONE	0.254	0.434	0.320
P	0.603	0.659	0.630

Macro-Precision: 0.439
Macro-Recall: 0.437
Macro-F1: 0.438