Chinese Microblogger character analysis using SVM

Microblogging provides a new platform for communicating and sharing information among Web users. Users can express opinions and record daily life using microblogs. Mircoblogs that are posted by users indicate the characters of users. In this paper, we focus on using Sina Weibo, the most popular Chinese microblogging platform, for the task of user character analysis. We define four categories features by analyzing microblogs, and show how to collect labeled corpus as training data. Using the corpus and via SVM (Support Vector Machines), we build a character classifier, which is able to determine extraversion or introversion for a microblogger. The experimental evaluations show that our method can identify users' character accurately and efficiently.