Evaluation - task1-intertass-ST4-PE
1428 tweets in qrel, 1428 tweets in run.

Accuracy: 0.382

Confusion matrix
Real	Pred.	#
N	NONE	132
N	P	111
N	N	170
N	NEU	59
NEU	NEU	45
NEU	P	134
NEU	NONE	122
NEU	N	66
NONE	NONE	57
NONE	P	63
NONE	NEU	13
NONE	N	26
P	NONE	70
P	N	51
P	P	274
P	NEU	35

Category evaluation
Cat	P	R	F1
N	0.543	0.360	0.433
NEU	0.296	0.123	0.173
NONE	0.150	0.358	0.211
P	0.471	0.637	0.542

Macro-Precision: 0.365
Macro-Recall: 0.370
Macro-F1: 0.367