Evaluation - task1-intertass-ST4-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.555

Confusion matrix
Real	Pred.	#
N	N	417
N	NONE	168
N	NEU	44
N	P	138
NEU	P	64
NEU	N	56
NEU	NEU	25
NEU	NONE	71
NONE	NONE	126
NONE	P	96
NONE	NEU	13
NONE	N	39
P	P	485
P	NONE	82
P	N	62
P	NEU	13

Category evaluation
Cat	P	R	F1
N	0.726	0.544	0.622
NEU	0.263	0.116	0.161
NONE	0.282	0.460	0.350
P	0.619	0.755	0.681

Macro-Precision: 0.473
Macro-Recall: 0.469
Macro-F1: 0.471