With the rapid growth of online social network services, influential analysis becomes a very interesting topic in this area. There are a lot of works have studied the problems related to this topic, and these works are mainly focused on identifying influential users, maximizing influence, and analyzing the relationship under different aspects. In this thesis, we propose a new influential measurement called WeiboRank, based on PageRank and Skyline methods, on a novel dataset, Sina Weibo, which is one of the largest online social network services in China. We also compared the differences between Sina Weibo and Twitter, which is rarely employed in China and analyzed the relationship between users in Sina Weibo based on tracing the source of influential. Our results show that we can accura...[ Read more ]

With the rapid growth of online social network services, influential analysis becomes a very interesting topic in this area. There are a lot of works have studied the problems related to this topic, and these works are mainly focused on identifying influential users, maximizing influence, and analyzing the relationship under different aspects. In this thesis, we propose a new influential measurement called WeiboRank, based on PageRank and Skyline methods, on a novel dataset, Sina Weibo, which is one of the largest online social network services in China. We also compared the differences between Sina Weibo and Twitter, which is rarely employed in China and analyzed the relationship between users in Sina Weibo based on tracing the source of influential. Our results show that we can accurately find the most influential individuals among the whole social network by considering all the available aspects, and for some specific user towards different factors via our method, which is better than the state-of-art.