Evaluation - task1-intertass-ST4-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.563

Confusion matrix
Real	Pred.	#
N	N	535
N	NONE	85
N	P	117
N	NEU	30
NEU	P	57
NEU	N	97
NEU	NONE	47
NEU	NEU	15
NONE	NONE	108
NONE	P	59
NONE	N	95
NONE	NEU	12
P	NONE	78
P	P	412
P	N	125
P	NEU	27

Category evaluation
Cat	P	R	F1
N	0.628	0.698	0.661
NEU	0.179	0.069	0.100
NONE	0.340	0.394	0.365
P	0.639	0.642	0.640

Macro-Precision: 0.446
Macro-Recall: 0.451
Macro-F1: 0.448