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

Accuracy: 0.485

Confusion matrix
Real	Pred.	#
N	N	391
N	NONE	220
N	P	75
N	NEU	81
NEU	NONE	92
NEU	N	51
NEU	P	53
NEU	NEU	20
NONE	NONE	174
NONE	N	32
NONE	NEU	31
NONE	P	37
P	NONE	186
P	P	336
P	NEU	63
P	N	57

Category evaluation
Cat	P	R	F1
N	0.736	0.510	0.602
NEU	0.103	0.093	0.097
NONE	0.259	0.635	0.368
P	0.671	0.523	0.588

Macro-Precision: 0.442
Macro-Recall: 0.440
Macro-F1: 0.441