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

Accuracy: 0.440

Confusion matrix
Real	Pred.	#
N	NONE	128
N	NEU	85
N	P	38
N	N	221
NEU	NONE	164
NEU	NEU	68
NEU	P	72
NEU	N	63
NONE	NONE	75
NONE	NEU	22
NONE	P	36
NONE	N	26
P	N	43
P	P	265
P	NONE	63
P	NEU	59

Category evaluation
Cat	P	R	F1
N	0.626	0.468	0.536
NEU	0.291	0.185	0.226
NONE	0.174	0.472	0.255
P	0.645	0.616	0.630

Macro-Precision: 0.434
Macro-Recall: 0.435
Macro-F1: 0.435