A trust calculating algorithm based on mobile phone data

Personalized mobile network service is a hotpot issue now. In order to provide the real-time and accurate personalized mobile network service, researchers introduce the trust into the mobile user need model. However the existing research rarely considers the context information and the structure of mobile social network when calculating the trust. Hence, in this paper, we propose a trust calculating algorithm which can improve the accuracy of the trust in mobile social network. Firstly, we analyze mobile users´ behaviors and incorporate the context into the trust calculating model. Secondly, the trust is introduced into the division of mobile community, and an improved method of mobile community division is proposed. Thirdly, according to the obtained mobile community structure, we propose a power calculating method and merge the trust and the obtained power. Finally, the similarity of contextual mobile user preferences is introduced into the trust. The experimental results show that our method can get more accurate community division and trust.