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

Accuracy: 0.583

Confusion matrix
Real	Pred.	#
N	N	600
N	P	103
N	NONE	44
N	NEU	20
NEU	N	103
NEU	P	74
NEU	NEU	9
NEU	NONE	30
NONE	N	104
NONE	NEU	16
NONE	P	96
NONE	NONE	58
P	NONE	42
P	P	441
P	N	139
P	NEU	20

Category evaluation
Cat	P	R	F1
N	0.634	0.782	0.701
NEU	0.138	0.042	0.064
NONE	0.333	0.212	0.259
P	0.618	0.687	0.650

Macro-Precision: 0.431
Macro-Recall: 0.431
Macro-F1: 0.431