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

Accuracy: 0.375

Confusion matrix
Real	Pred.	#
N	NEU	239
N	P	44
N	NONE	63
N	N	126
NEU	NEU	177
NEU	N	54
NEU	NONE	79
NEU	P	57
NONE	NEU	69
NONE	NONE	37
NONE	P	26
NONE	N	27
P	N	51
P	NEU	132
P	P	195
P	NONE	52

Category evaluation
Cat	P	R	F1
N	0.488	0.267	0.345
NEU	0.287	0.482	0.360
NONE	0.160	0.233	0.190
P	0.606	0.453	0.519

Macro-Precision: 0.385
Macro-Recall: 0.359
Macro-F1: 0.372