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

Accuracy: 0.544

Confusion matrix
Real	Pred.	#
N	N	478
N	NEU	126
N	NONE	81
N	P	82
NEU	NEU	57
NEU	N	70
NEU	P	56
NEU	NONE	33
NONE	NONE	111
NONE	NEU	59
NONE	P	51
NONE	N	53
P	NONE	74
P	P	388
P	NEU	95
P	N	85

Category evaluation
Cat	P	R	F1
N	0.697	0.623	0.658
NEU	0.169	0.264	0.206
NONE	0.371	0.405	0.387
P	0.672	0.604	0.637

Macro-Precision: 0.477
Macro-Recall: 0.474
Macro-F1: 0.476