Enhancing Privacy using Community Driven Recommendations: An Investigation with Facebook Data

User specific information in social media is sensitive and subject to privacy. Continuously changing privacy policies and configuration procedures in social media require users to constantly educate themselves of the changes. A collective intelligence driven approach, known as Collective-Context Based Privacy Model (C-CBPM) has been developed that recommends privacy policies based on community and trust gleaned from social network information. By defining userspecified contexts, C-CBPM advances the existing content, user, or role-based privacy models. This research examines the efficacy of C-CBPM using Facebook data comprising of 957,359 users, 957,357 connections, and 32,176 communities. Objective trust and privacy risk assessment measures are developed. Results indicate promising findings with 83% correct recommendations. Out of the 17% incorrect recommendations, almost all (i.e., 99.24% of the incorrect recommendations) incur only 25% risk and only 0.018% incur 100% or maximum risk, in the worst-case scenario. The results demonstrate the feasibility of the C-CBPM in real-world for community driven privacy recommendations.