Interest- And Content-Based Data Dissemination In Mobile Social Networks

GLOBECOM 2017 - 2017 IEEE GLOBAL COMMUNICATIONS CONFERENCE(2017)

引用 1|浏览0
暂无评分
摘要
With the increasing popularity of hand-held mobile devices such as smart phones and smart watches, people are connected more than ever, which enables the information to be created, forwarded, and exchanged at levels that one could not envision just a few years ago. Mobile social networks (MSNs) thrive with the popularity of mobile smart devices and exhibit the properties of social networks. To efficiently disseminate the information within MSNs, there have been research efforts on content-based routing schemes which rely on the network structure and user interest profiles. However, none of these prior works considered the impact of data content during data dissemination in MSNs. However such content is closely related to users' preferences, which have a significant influence on the result of the dissemination. To fill this void, we propose an interest-and content-based dissemination scheme in MSNs, where the contents of the messages, along with the network structural information are taken into consideration. In the proposed scheme, each user is associated with an interest profile and each message is associated with a message content profile. Similarities are measured between the users and the messages given their profiles. We also use PageRank to measure the importance of each user when the network evolves over time. Each piece of information is propagated based on the similarity scores and PageRank selection of relay users. We experimentally show that the proposed scheme achieves higher delivery performance compared to the existing schemes while remaining cost-effective.
更多
查看译文
关键词
mobile social networks,MSNs,mobile smart devices,content-based routing schemes,network structure,data content,network structural information,interest profile,message content profile,relay users,increasing popularity,content-based data dissemination,interest-based data dissemination
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要