Targeted Advertising That Protects the Privacy of Social Networks Users

Nowadays, the massive use of social media provides useful unstructured knowledge that can be used to enhance the efficacy of online brand marketing campaigns. The unstructured nature of social media content and the relevance of the contextual dimension, like time, stress the requirements for extracting users' interests during the timeline. However, user profiling could have some unpleasant consequences for users' privacy, thus raising the need to define methodologies capable of avoiding privacy leaks despite the exploitation of interactions over social media. This paper presents both an intelligent method of profiling social media users and a privacy protection technique that is designed to match users' profiles and advertisements, and which could be used by advertising agencies. The proposed method performssemantic data analysis for extracting representations of the contents of messages exchanged by users over social media (e.g.,tweets), by exploiting rough set theory. In this way, users' interestis obtained by mining their daily online activity. The proposed framework investigates two-party scenarios, i.e., scenarios composed of a social network owner and an advertising agency willing to promote its client's products through the social network. This paper presents three privacy-preserving matching protocols which enable targeted advertising without compromising the privacy of either the users or the advertisers. Starting from a recently proposed advertisement matching protocol, a private layer was added to ensure that any sensitive information of either party is kept private. In this way, the social network and the advertiser could benefit from a system which allows them to run a matching protocol with the guarantee that sensitive user data (for the social network) and business information (for the advertiser) will not be disclosed. The first two protocols require interaction between the Advertiser and the Online Social Network, while the third one outsources to a semi-trusted service provider some of the computation done during the execution of the advertisement matching. The experimental results are also presented to illustrate the proposed system's good performance to discover potentially interested users given an advertisement as input.