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

Accuracy: 0.584

Confusion matrix
Real	Pred.	#
N	N	495
N	NEU	43
N	NONE	107
N	P	122
NEU	P	65
NEU	N	81
NEU	NEU	19
NEU	NONE	51
NONE	NONE	115
NONE	P	89
NONE	N	58
NONE	NEU	12
P	P	480
P	NONE	65
P	N	83
P	NEU	14

Category evaluation
Cat	P	R	F1
N	0.690	0.645	0.667
NEU	0.216	0.088	0.125
NONE	0.340	0.420	0.376
P	0.635	0.748	0.687

Macro-Precision: 0.470
Macro-Recall: 0.475
Macro-F1: 0.473