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

Accuracy: 0.124

Confusion matrix
Real	Pred.	#
N	NONE	444
N	N	17
N	P	11
NEU	NONE	348
NEU	N	15
NEU	P	4
NONE	NONE	149
NONE	P	2
NONE	N	8
P	NONE	400
P	P	11
P	N	19

Category evaluation
Cat	P	R	F1
N	0.288	0.036	0.064
NEU	0.000	0.000	0.000
NONE	0.111	0.937	0.199
P	0.393	0.026	0.048

Macro-Precision: 0.198
Macro-Recall: 0.250
Macro-F1: 0.221