User Preference Mining and Privacy Policy Recommendation for Social Networks

Nowadays, more and more people rely on web-based social network services not only for entertainment but also for work. There are a lot of user data such as profiles and actions are stored on these social platforms. Privacy setting is an important means to protect these private data. To help users better manage their private information, we propose a user preference based privacy policy recommendation approach for the currently popular modes of privacy management. We investigate user preferences from their privacy policies and recommend similar settings when a new friend is added or a new item is uploaded. To evaluate our methods, we propose several criteria and perform a lot of experiments on some practical datasets. The experimental results show that our algorithms are applicable for both person assignments and item management.