Table 5. AUC of prediction results using different co-tag features within t early hours.

Prediction features include the number of tweets containing the co-tags (T), the number of co-tag adopters (A), the diversity of co-tags (H ₂), and the number of observed co-tags (m). The threshold is expressed as a top percentile of most popular hashtags that are deemed viral for evaluation purposes. Best results for each column are bolded.

Threshold	50%			10%			1%			0.1%
t (hour)	1	6	24	1	6	24	1	6	24	1	6	24
T	0.50	0.51	0.52	0.51	0.53	0.55	0.58	0.62	0.66	0.66	0.72	0.75
A	0.50	0.50	0.52	0.50	0.52	0.54	0.58	0.62	0.65	0.65	0.71	0.74
H 2	0.50	0.51	0.53	0.52	0.54	0.57	0.61	0.66	0.70	0.70	0.77	0.82
m	0.52	0.53	0.55	0.55	0.58	0.61	0.64	0.70	0.75	0.72	0.81	0.86
m + T †	0.52	0.53	0.55	0.54	0.57	0.61	0.64	0.70	0.75	0.72	0.81	0.86
m + A †	0.52	0.53	0.55	0.55	0.57	0.61	0.64	0.70	0.75	0.72	0.81	0.86
m + H 2 †	0.55	0.55	0.57	0.58	0.60	0.63	0.66	0.70	0.75	0.74	0.81	0.86

† A linear combination with coefficients determined by regression fitting using least squared error.