Evaluation - task1-intertass-ST4-CR
1233 tweets in qrel, 1233 tweets in run.

Accuracy: 0.440

Confusion matrix
Real	Pred.	#
N	N	205
N	NONE	140
N	NEU	57
N	P	89
NEU	NONE	46
NEU	N	44
NEU	P	43
NEU	NEU	31
NONE	N	35
NONE	P	67
NONE	NONE	101
NONE	NEU	21
P	NONE	75
P	P	206
P	NEU	26
P	N	47

Category evaluation
Cat	P	R	F1
N	0.619	0.418	0.499
NEU	0.230	0.189	0.207
NONE	0.279	0.451	0.345
P	0.509	0.582	0.543

Macro-Precision: 0.409
Macro-Recall: 0.410
Macro-F1: 0.409