Competition-Based Benchmarking of Influence Ranking Methods in Social Networks

Table 4

Comparison between individual SIR and our simultaneous competition-based benchmark in terms of how well ranking methods are differentiated. is the difference (%) between the most and least efficient ranking methods; is the difference (%) between the top 2 ranking methods on each dataset. Higher differences are better.

	(%)	Rand	Mesh	SW	SF	OSN	FB	Emails	POK
SIR		0.31	0.06	1.59	3.28	0.99	0.15	1.58	1.17
Competition		98.72	92.32	85.19	97.09	96.05	83.12	96.25	80.07
SIR		0.07	0.00	0.18	1.07	0.33	0.00	0.80	0.02
Competition		0.28	2.73	6.5	1.72	2.46	8.76	0.71	5.37