Understanding the top grass roots in sina-weibo

  • Authors:
  • Ze Huang;Bo Yuan;Xuelei Hu

  • Affiliations:
  • Intelligent Computing Lab, Division of Informatics, Graduate School at Shenzhen, Tsinghua University, Shenzhen, P.R. China;Intelligent Computing Lab, Division of Informatics, Graduate School at Shenzhen, Tsinghua University, Shenzhen, P.R. China;School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, P.R. China

  • Venue:
  • IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Microblogging is now popular among everyday web users in China who have a common name called grass roots in Sina-Weibo, a major microblogging service similar to Twitter. In this paper, we investigate the properties of messages published by this group of users and classify the messages into various topic categories using text classification methods based on the Bag of Words (BOW) model. We find that, using Naïve Bayes, it is possible to achieve high accuracy in recognizing the topic of a message but the popularity of a message cannot be reliably predicated based on its contents. These findings are also further explored with visualization techniques.