The Friends-Oriented Reputation Privacy Score (FORPS) system provides a smart and simple way to help end-users managing their privacy in a social network. It aims to prevent a non-desirable propagation of personal sensitive data. FORPS built privacy sensitivity profile by understanding what are the category of themes, the category of objects and the behavioral factors that are important to social network users. FORPS takes full advantage of the knowledge available in a social network from the perspective of a given user, in particular extracted from the data accessible via his friends. More precisely, our approach consists in making a deep analysis of the behavior of somebody who would like to establish connection with the given user in order to estimate the risk of potential violation of his privacy.