Evaluation - task1-intertass-PE
1428 tweets in qrel, 1428 tweets in run.

Accuracy: 0.403

Confusion matrix
Real	Pred.	#
N	NEU	302
N	P	44
N	N	126
NEU	NEU	254
NEU	N	56
NEU	P	57
NONE	NEU	105
NONE	P	26
NONE	N	28
P	N	50
P	NEU	185
P	P	195

Category evaluation
Cat	P	R	F1
N	0.485	0.267	0.344
NEU	0.300	0.692	0.419
NONE	0.000	0.000	0.000
P	0.606	0.453	0.519

Macro-Precision: 0.348
Macro-Recall: 0.353
Macro-F1: 0.350