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

Accuracy: 0.660

Confusion matrix
Real	Pred.	#
N	N	568
N	NEU	76
N	NONE	51
N	P	72
NEU	NONE	36
NEU	N	60
NEU	P	75
NEU	NEU	45
NONE	NONE	123
NONE	N	61
NONE	NEU	29
NONE	P	61
P	NEU	47
P	P	517
P	NONE	38
P	N	40

Category evaluation
Cat	P	R	F1
N	0.779	0.741	0.759
NEU	0.228	0.208	0.218
NONE	0.496	0.449	0.471
P	0.713	0.805	0.756

Macro-Precision: 0.554
Macro-Recall: 0.551
Macro-F1: 0.552