Social Media involve many shared items, such as photos, which may concern more than one user. The challenge is that users’ individual privacy preferences for the same item may conflict, so an approach that just merges in some way the users’ privacy preferences may provide unsatisfactory results. Previous proposals to deal with the problem were either time-consuming or did not consider compromises to solve these conflicts (e.g., by considering unilaterally-imposed approaches only). We propose a negotiation mechanism for users to agree on a compromise for the conflicts found. The second challenge we address in this paper relates to the exponential complexity of such a negotiation mechanism. To address this, we propose heuristics that reduce the complexity of the negotiation mechanism and show how substantial benefits can be derived from the use of these heuristics through extensive experimental evaluation that compares the performance of the negotiation mechanism with and without these heuristics. Moreover, we show that one such heuristic makes the negotiation mechanism produce results fast enough to be used in actual Social Media infrastructures with near-optimal results.
|Number of pages||29|
|Journal||ACM Transactions on Autonomous and Adaptive Systems|
|Publication status||Published - 9 Feb 2016|
- School of Informatics - Personal Chair of Artificial Intelligence
- Artificial Intelligence and its Applications Institute
- Data Science and Artificial Intelligence
Person: Academic: Research Active