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

Accuracy: 0.427

Confusion matrix
Real	Pred.	#
N	N	379
N	P	167
N	NEU	179
N	NONE	42
NEU	P	76
NEU	N	60
NEU	NONE	20
NEU	NEU	60
NONE	NEU	118
NONE	NONE	40
NONE	P	87
NONE	N	29
P	N	107
P	NEU	181
P	P	331
P	NONE	23

Category evaluation
Cat	P	R	F1
N	0.659	0.494	0.565
NEU	0.112	0.278	0.159
NONE	0.320	0.146	0.201
P	0.501	0.516	0.508

Macro-Precision: 0.398
Macro-Recall: 0.358
Macro-F1: 0.377