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

Accuracy: 0.524

Confusion matrix
Real	Pred.	#
N	NEU	96
N	NONE	128
N	P	192
N	N	351
NEU	NONE	53
NEU	N	42
NEU	P	86
NEU	NEU	35
NONE	NONE	109
NONE	P	108
NONE	N	38
NONE	NEU	19
P	NONE	71
P	P	501
P	N	43
P	NEU	27

Category evaluation
Cat	P	R	F1
N	0.741	0.458	0.566
NEU	0.198	0.162	0.178
NONE	0.302	0.398	0.343
P	0.565	0.780	0.655

Macro-Precision: 0.451
Macro-Recall: 0.449
Macro-F1: 0.450