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

Accuracy: 0.544

Confusion matrix
Real	Pred.	#
N	N	481
N	P	238
N	NONE	44
N	NEU	4
NEU	P	105
NEU	N	97
NEU	NEU	3
NEU	NONE	11
NONE	N	110
NONE	P	128
NONE	NONE	35
NONE	NEU	1
P	P	515
P	N	100
P	NONE	23
P	NEU	4

Category evaluation
Cat	P	R	F1
N	0.610	0.627	0.619
NEU	0.250	0.014	0.026
NONE	0.310	0.128	0.181
P	0.522	0.802	0.633

Macro-Precision: 0.423
Macro-Recall: 0.393
Macro-F1: 0.407