The work presented in this paper focuses on opportunistic routing in distributed Mobile Social Networks (MSNs). It proposes a novel routing protocol called Socially-Aware Multi-Phase Opportunistic (SAMPhO), where the routing procedure for each message is carried out in multiple phases. From the various socially aware metrics considered, ego-betweenness and tie strength are selected to be utilized according to the conditions of the social environment. Previous research on the area suggests that different metrics are useful in different conditions. However, only recently steps towards this direction are taken. To evaluate the proposed hypothesis, a simulated delay tolerant MSN was introduced in the OMNeT++ environment using a framework, developed as part of this work. It is called Socially-Aware Opportunistic Routing System (SAORS) and its modular design facilitates further research in opportunistic networks. The routing mechanism is divided in three independent stages, with SAORS focusing on providing the necessary functionality for the first one. The simulation results drawn clearly demonstrate the scalability and improved performance of SAMPhO, especially in highly social scenarios. It is shown to be both more efficient and effective than previous algorithms, in terms of bandwidth and memory utilization, and delivery rates respectively. However, it relies greatly on the accuracy of the social tie detection, since the copy generation is very limited.
