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

Accuracy: 0.547

Confusion matrix
Real	Pred.	#
N	P	138
N	N	572
N	NONE	30
N	NEU	27
NEU	P	69
NEU	N	120
NEU	NONE	15
NEU	NEU	12
NONE	P	109
NONE	NONE	34
NONE	NEU	13
NONE	N	118
P	NONE	18
P	P	420
P	NEU	24
P	N	180

Category evaluation
Cat	P	R	F1
N	0.578	0.746	0.651
NEU	0.158	0.056	0.082
NONE	0.351	0.124	0.183
P	0.571	0.654	0.610

Macro-Precision: 0.414
Macro-Recall: 0.395
Macro-F1: 0.404