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

Accuracy: 0.577

Confusion matrix
Real	Pred.	#
N	P	116
N	N	588
N	NEU	21
N	NONE	42
NEU	P	77
NEU	N	113
NEU	NONE	15
NEU	NEU	11
NONE	N	102
NONE	NONE	55
NONE	P	106
NONE	NEU	11
P	N	161
P	P	442
P	NEU	20
P	NONE	19

Category evaluation
Cat	P	R	F1
N	0.610	0.767	0.679
NEU	0.175	0.051	0.079
NONE	0.420	0.201	0.272
P	0.596	0.688	0.639

Macro-Precision: 0.450
Macro-Recall: 0.427
Macro-F1: 0.438