Abstract: Recently, Micro-blog has attracted more and more interests of Internet users. Thousands of the users share their views and opinions through micro-blog. There arc a large number of texts with sentiment orientation (thinking something is "good" or "bad") on the Micro-blog. These texts reflect the authors' emotion. Investor sentiment is the important indicator to research on the economic market trends. On behavioral finance, Stock investor sentiment affects the investors' decision. I}hen it will affect stock market. The stock investor sentiment orientation (thinking the future market will be "good" or "bad") on the future stock market is the indicator to reflect the investor emotion. In this paper,we proposed a method of sentiment classification and apply it to perform sentiment classification on Sina micro-blog (currently,thc largest Chinese micro-blog platform). In detail, our approach contains two-step classifier. Firstly, the first classifier will identify the sentence that contains the future sentiment. Secondly, use the second classifier to classify the sentence which identified by the first classifier into positive or negative. I}he experimental results show that our method achieves a decent performance on identifying the future stock investor sentiment orientation.

Key words: Computer application, Chinese information processing, Investor sentiment, Micro-blog, Sentiment classificalion, Sentiment orientation