基于社交网络的图像广告系统

A social-network-based image advertising system

提出一种基于社交网络,整合用户影响力、上下文内容相关性、局部内容相关性的上下文相关图像广告系统,同时优化广告的传播效果和上下文内容相关性以实现广告、图像页面、图像嵌入点的关联.并将以上广告关联问题建模为一个非线性0-1整数规划问题,采用启发式搜索降低了最优化搜索的计算量.实验结果表明,以最流行的图像分享社交网站Flickr为广告平台,通过最优化用户影响力、上下文内容相关性和局部内容相关性,取得了较好的广告相关性和用户评价.

A social-network-based image advertising system was proposed, which integrated the user influence, contextual relevance and local relevance and simultaneously optimized the dissemination of advertising and contextual relevance, as well as the insertion point of advertisement. Then, the advertising problem was formulated as a non-linear 0-1 integer programming problem. Moreover, a heuristic search scheme was proposed to reduce the computation consumption. Experimental results show that, on the most popular image sharing site, Flickr, the system achieves good relevance and encouraging user satisfactioru .