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

Accuracy: 0.530

Confusion matrix
Real	Pred.	#
N	NONE	99
N	NEU	79
N	N	460
N	P	129
NEU	P	78
NEU	N	73
NEU	NONE	28
NEU	NEU	37
NONE	N	57
NONE	NONE	106
NONE	P	64
NONE	NEU	47
P	N	98
P	P	404
P	NEU	71
P	NONE	69

Category evaluation
Cat	P	R	F1
N	0.669	0.600	0.632
NEU	0.158	0.171	0.164
NONE	0.351	0.387	0.368
P	0.599	0.629	0.614

Macro-Precision: 0.444
Macro-Recall: 0.447
Macro-F1: 0.445