A Tool for Retrieving Meaningful Privacy Information from Social Networks

The use of social networking services (SNSs) such as Facebook, Flickr, or MySpace has grown explosively in the last few years. People see these SNSs as useful tools to find friends and interact with them. SNSs allow their users to share photos, videos, and express their thoughts and feelings. Even though users enjoy the capabilities that these SNSs offer, they have became aware of privacy issues. The public image of a subject can be affected by photos or comments posted on a social network. Therefore it is important for SNS users to control what others can see in their profile. Recent studies demonstrate that users are demanding better mechanisms to protect their privacy. An appropriate approximation to solve this problem is a tool that automatically suggests a privacy policy for any item shared on a SNS. The first step for any mechanism to recommend and predict privacy policies is to retrieve meaningful privacy information from the SNS, such user communities and the relationships of them. Most SNSs rely on groups to help users specify their privacy policies. Therefore, a basic functionality of such a mechanism is to group the user’s friends automatically. Although SNSs treat all of the friends of a user the same, without taking into account different degrees of the friendship, this is not a realistic approach. Hence, another factor to consider when defining a privacy policy is the type of relationship between the owner of the item being shared and its potential viewers. In this work, we present a tool called Best Friend Forever (BFF) that automatically classifies the friends of a user in communities and assigns a value to the strength of the relationship ties to each one. We also explain the characteristics of BFF and show the results of an experimental evaluation.