MoCA: a novel privacy-preserving contextual advertising platform on mobile devices

Jung-Hyun Lee, Woo-Jong Ryu, Kang-Min Kim, SangKeun Lee

Abstract: In this work, we propose a novel contextual advertising platform, called MoCA, which is designed to improve the relevance of in-app advertising in a stand-alone, privacy-protecting manner on mobile devices. MoCA understands the semantics of the current app page and matches semantically relevant ads inside mobile devices. In addition, MoCA controls the degree of privacy protection per user by utilizing a novel semantic generalization model on top of topical taxonomy. Our experimental results verify the effectiveness and feasibility of MoCA with minimal system overheads in terms of runtime, memory usage, and energy consumption.. To the best of our knowledge, this is one of few work on the mobile contextual advertising platform without resort to ad servers.