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

Accuracy: 0.667

Confusion matrix
Real	Pred.	#
N	N	623
N	NEU	26
N	P	73
N	NONE	45
NEU	NONE	36
NEU	N	82
NEU	P	74
NEU	NEU	24
NONE	NONE	107
NONE	P	72
NONE	N	83
NONE	NEU	12
P	NONE	43
P	P	512
P	N	63
P	NEU	24

Category evaluation
Cat	P	R	F1
N	0.732	0.812	0.770
NEU	0.279	0.111	0.159
NONE	0.463	0.391	0.424
P	0.700	0.798	0.746

Macro-Precision: 0.544
Macro-Recall: 0.528
Macro-F1: 0.536