CHINESE OPINIONATED INFORMATION PREDICTING BASED-ON SOCIAL BEHAVIOR
Monitoring the on-line opinions is becoming more and more important. In this paper, we have designed two experiments for Chinese opinionated information prediction which are based on social behavior. The first experiment have made an analysis of a corpus of tens of thousands of opinions on a famous tragedy “Antigone. These opinions indicated significant differences in writing styles and subjects between male and female writers as well as among reviewers of different ages. Such differences can be exploited to determine an unknown author’s age and gender on the new opinions emerging in the future. The second experiment, we detected the time-series of the development of opinions. The corpus is tens of thousands on-line opinions with time-series on a specific issue.
trend predict social behavior
Zhe Jia Cong Wang
School of Information Engineering,Beijing University of Posts and Telecommunications,Beijing,China
国际会议
2008年拟人系统国际会议(2008 International Conference on Humanized Systems )(ICHS’08)
北京
英文
2008-10-18（万方平台首次上网日期，不代表论文的发表时间）