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

Accuracy: 0.534

Confusion matrix
Real	Pred.	#
N	P	101
N	NEU	46
N	N	530
N	NONE	90
NEU	P	48
NEU	N	125
NEU	NEU	15
NEU	NONE	28
NONE	N	101
NONE	NEU	30
NONE	P	54
NONE	NONE	89
P	P	381
P	N	166
P	NEU	28
P	NONE	67

Category evaluation
Cat	P	R	F1
N	0.575	0.691	0.628
NEU	0.126	0.069	0.090
NONE	0.325	0.325	0.325
P	0.652	0.593	0.622

Macro-Precision: 0.420
Macro-Recall: 0.420
Macro-F1: 0.420