Sentiment analysis on Weibo data

Abstract

With the development of the Internet, people share their emotion statuses or attitudes on online social websites, leading to an explosive rise on the scale of data. Mining sentiment information behind these data helps people know about public opinions and social trends. In this paper a sentiment analysis algorithm adapting to Weibo (Microblog) data is proposed. Given that a Weibo post is usually short, LDA model is used to generate text features based on semantic information instead of text structure. To decide the sentiment polar and degree, SVR model is used here. Experiment shows the algorithm performs well on Weibo data.