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

Accuracy: 0.576

Confusion matrix
Real	Pred.	#
N	P	121
N	N	583
N	NEU	26
N	NONE	37
NEU	P	79
NEU	N	110
NEU	NONE	17
NEU	NEU	10
NONE	NEU	18
NONE	NONE	55
NONE	P	100
NONE	N	101
P	N	151
P	P	446
P	NEU	22
P	NONE	23

Category evaluation
Cat	P	R	F1
N	0.617	0.760	0.681
NEU	0.132	0.046	0.068
NONE	0.417	0.201	0.271
P	0.598	0.695	0.643

Macro-Precision: 0.441
Macro-Recall: 0.425
Macro-F1: 0.433