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

Accuracy: 0.592

Confusion matrix
Real	Pred.	#
N	N	608
N	NEU	24
N	NONE	38
N	P	97
NEU	N	119
NEU	P	59
NEU	NONE	24
NEU	NEU	14
NONE	NONE	73
NONE	N	112
NONE	P	80
NONE	NEU	9
P	P	429
P	N	145
P	NONE	50
P	NEU	18

Category evaluation
Cat	P	R	F1
N	0.618	0.793	0.694
NEU	0.215	0.065	0.100
NONE	0.395	0.266	0.318
P	0.645	0.668	0.656

Macro-Precision: 0.468
Macro-Recall: 0.448
Macro-F1: 0.458