TiSA: Time-dependent social network advertising

Abstract

Much of today's online social network (OSN) system relies on advertising for financial support. To improve the effectiveness of advertising, online advertisers tend to leverage influential users to deliver ads. Most of existing efforts on online advertising have focused on single-shot scenarios or assume static OSN models, while they overlook the fact that actions of advertising affect users' behaviors. In this paper, we investigate the behaviors of Sina Weibo users over three months, and make the observation that advertising affects the behaviors of the user's followers, which in turn has an impact on the effectiveness of future advertising. Based on this observation, we propose TiSA, a time-dependent advertising framework, which considers the future impact of advertising. Under this framework, the advertiser and the user make their decisions based on their instant utilities as well as future utilities. We also devise a learning algorithm with provable convergence to obtain the optimal policies. Evaluations using three month traces of 975 Sina Weibo users have been conducted, and the results validate the effectiveness of the proposed framework by showing that the utilities of all entities are significantly improved compared with traditional systems.