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

Accuracy: 0.528

Confusion matrix
Real	Pred.	#
N	P	168
N	N	518
N	NONE	49
N	NEU	32
NEU	N	95
NEU	P	82
NEU	NEU	15
NEU	NONE	24
NONE	N	128
NONE	P	88
NONE	NONE	43
NONE	NEU	15
P	P	427
P	N	154
P	NONE	43
P	NEU	18

Category evaluation
Cat	P	R	F1
N	0.579	0.675	0.623
NEU	0.188	0.069	0.101
NONE	0.270	0.157	0.199
P	0.558	0.665	0.607

Macro-Precision: 0.399
Macro-Recall: 0.392
Macro-F1: 0.395