Table 1. Mean absolute errors from cross-validation across three seasons for the “nowcasting” task.

(a) Final revised CDC weekly estimates; (b) the realistic model using original CDC data before revision; (c) the model augmented with Twitter data; (d) the model augmented with GFT data; (e) the model augmented with both Twitter and GFT data; (f) values predicted by measuring the historical average.

	Model	11-12	12-13	13-14
(a)	Revised CDC (y)	0.10	0.24	0.24
(b)	Original CDC (~y)	0.20	0.30	0.32
(c)	Twitter (z)	0.33	0.36	0.48
	Twitter (z) + Original CDC (~y)	0.14	0.21	0.21
(d)	GFT (z)	0.35	0.71	0.89
	GFT (z) + Original CDC (~y)	0.20	0.45	0.28
(e)	Twitter + GFT (z)	0.24	0.67	0.62
	Twitter + GFT (z) + Original CDC (~y)	0.15	0.33	0.21
(f)	Historical Average (~y)	0.95	0.87	1.39