Detecting Privacy Preferences from Online Social Footprints: A Literature Review

Abstract

Providing personalized content can be of great value to both users and vendors. However, effective personalization hinges on collecting large amounts of personal data about users. With the exponential growth of activities in social networking websites, they have become a prominent platform to gather and analyze such information. Even though there exist a considerable number of social media users with publicly available data, previous studies have revealed a dichotomy between privacy-related intentions and behaviours. Users often face difficulties specifying privacy policies that are consistent with their actual privacy concerns and attitudes, and simply follow the default permissive privacy setting. Therefore, despite the availability of data, it is imperative to develop and employ algorithms to automatically predict users’ privacy preferences for personalization purposes. In this document, we review prior studies that tackle this challenging task and make use of users’ online social footprints to discover their desired privacy settings.