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

Accuracy: 0.590

Confusion matrix
Real	Pred.	#
N	N	527
N	NEU	33
N	P	161
N	NONE	46
NEU	P	91
NEU	N	95
NEU	NONE	17
NEU	NEU	13
NONE	NONE	67
NONE	P	125
NONE	N	73
NONE	NEU	9
P	P	513
P	N	97
P	NEU	5
P	NONE	27

Category evaluation
Cat	P	R	F1
N	0.665	0.687	0.676
NEU	0.217	0.060	0.094
NONE	0.427	0.245	0.311
P	0.576	0.799	0.670

Macro-Precision: 0.471
Macro-Recall: 0.448
Macro-F1: 0.459