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

Accuracy: 0.572

Confusion matrix
Real	Pred.	#
N	N	453
N	P	187
N	NEU	45
N	NONE	82
NEU	P	97
NEU	N	65
NEU	NONE	33
NEU	NEU	21
NONE	NONE	89
NONE	P	120
NONE	NEU	10
NONE	N	55
P	P	524
P	NONE	40
P	N	71
P	NEU	7

Category evaluation
Cat	P	R	F1
N	0.703	0.591	0.642
NEU	0.253	0.097	0.140
NONE	0.365	0.325	0.344
P	0.565	0.816	0.668

Macro-Precision: 0.471
Macro-Recall: 0.457
Macro-F1: 0.464