Weibo Clustering: A New Approach Utilizing Users’ Reposting Data in Social Networking Services

Guangzhi Zhang, Yunchuan Sun, Mengling Xu, Rongfang Bie

As one of the most popular Social Networking Services (SNS) in China, Weibo is generating massive contents, relations and users’ behavior data. Many challenges exist in how to analyze Weibo data. Most works focus on Weibo clustering and topic classification based on analyzing the text contents only. However, the traditional approaches do not work well because most messages on Weibo are very short Chinese sentences. This paper aims to propose a new approach to cluster the Weibo data by analyzing the users’ reposting behavior data besides the text contents. To verify the proposed approach, a data set of users’ real behaviors from the actual SNS platform is utilized. Experimental results show that the proposed method works better than previous works which depend on the text analysis only.