Microblogging as a social sensing tool

Microblogging has become a popular communication tool among Internet users. Millions of users retrieve information and share opinions on different aspects of their daily lives using this platform. This paper presents the development of an online microblog collection and analysis tool that automatically collects public tweets from Chinese microblogging site - Sina Weibo and employs the data processing techniques from Hadoop platform to perform linguistic analysis of the collected data (Chinese characters). We show examples and procedures to use our tool on Chinese posting with GBK and UTF-8 encodings. We demonstrate the tool as a social sensing tool by providing geographical locations on air pollution topic in Sina Weibo. The proposed techniques can be used to analyze online posts in other languages and can be used for online social behavior study.