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

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