Evaluation - task1-intertass-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.433

Confusion matrix
Real	Pred.	#
N	NONE	211
N	N	307
N	P	145
N	NEU	104
NEU	NONE	69
NEU	N	51
NEU	P	68
NEU	NEU	28
NONE	NONE	112
NONE	P	95
NONE	N	44
NONE	NEU	23
P	NONE	143
P	P	376
P	NEU	42
P	N	81

Category evaluation
Cat	P	R	F1
N	0.636	0.400	0.491
NEU	0.142	0.130	0.136
NONE	0.209	0.409	0.277
P	0.550	0.586	0.567

Macro-Precision: 0.384
Macro-Recall: 0.381
Macro-F1: 0.383