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

Accuracy: 0.523

Confusion matrix
Real	Pred.	#
N	NONE	57
N	N	577
N	P	121
N	NEU	12
NEU	P	55
NEU	N	126
NEU	NONE	33
NEU	NEU	2
NONE	N	142
NONE	P	71
NONE	NONE	54
NONE	NEU	7
P	NONE	44
P	P	360
P	N	225
P	NEU	13

Category evaluation
Cat	P	R	F1
N	0.539	0.752	0.628
NEU	0.059	0.009	0.016
NONE	0.287	0.197	0.234
P	0.593	0.561	0.576

Macro-Precision: 0.370
Macro-Recall: 0.380
Macro-F1: 0.375