Enhancing Recommendations in Mobile Social Network

Abstract

In Mobile Social Networks (MSNs), people contact each other through mobile devices, such as smartphones and tablets, while they move freely. The communication takes place on-the-fly by the opportunistic contacts between mobile users via local wireless bandwidth, such as Bluetooth or WiFi without a network infrastructure. Social Multicast is an important routing service in MSNs where data transmission is addressed to a group of users according to their social features. The aim of this paper is to find and recommend mobile nodes that can efficiently relay and consume messages based on their social features. Efficiency in this context is to achieve high delivery ratio while reducing considering resources constraints and limitations such as power and space. The proposed algorithm, TESS, measures social similarity based on Time-based Encounter of Socially Similar nodes. We compare the proposed algorithm with the known social multicast algorithms: Multi-CSDO, EncoCent and Epidemic. Simulations results show that the proposed algorithm outperforms others in terms of delivery ratio and network overhead.