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

Accuracy: 0.549

Confusion matrix
Real	Pred.	#
N	N	437
N	NEU	138
N	NONE	118
N	P	74
NEU	NONE	57
NEU	N	55
NEU	P	37
NEU	NEU	67
NONE	NONE	133
NONE	P	51
NONE	N	28
NONE	NEU	62
P	P	406
P	NONE	84
P	NEU	91
P	N	61

Category evaluation
Cat	P	R	F1
N	0.752	0.570	0.648
NEU	0.187	0.310	0.233
NONE	0.339	0.485	0.399
P	0.715	0.632	0.671

Macro-Precision: 0.498
Macro-Recall: 0.499
Macro-F1: 0.499