Abstract: For the problems of lacking standardization on criterion of Uighur sentiment corpus, small scale corpus， and no suitable tagging system, we built a tagging criterion for Uighur sentiment corpus by analyzing the advantages of famous sentiment corpuses in English and Chinese and combining the characteristics of Uighur text. We also developed a tagging system which can collect data from the Internet using Python language and built a Uighur sentiment corpus. The corpus can be used in the analysis of public opinion. Experimental results show that the tagging criterion is of expandability and practicability, the tagging system can effectively reduce the workload and improve the quality of sentiment corpus, and the sentiment corpus can be used for the public opinion analysis task.


Key words: computer application, natural language processing, sentiment analysis, Uighur, sentiment corpus