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

Accuracy: 0.647

Confusion matrix
Real	Pred.	#
N	N	579
N	NEU	80
N	P	47
N	NONE	61
NEU	NONE	55
NEU	N	65
NEU	P	48
NEU	NEU	48
NONE	NONE	152
NONE	N	47
NONE	P	43
NONE	NEU	32
P	NEU	67
P	P	450
P	NONE	74
P	N	51

Category evaluation
Cat	P	R	F1
N	0.780	0.755	0.767
NEU	0.211	0.222	0.217
NONE	0.444	0.555	0.494
P	0.765	0.701	0.732

Macro-Precision: 0.550
Macro-Recall: 0.558
Macro-F1: 0.554