Emotion Recognition from Text based on the Rough Set Theory and the Support Vector Machines

In recent years, several methods on human emotion recognition have been published. But computer application on Chinese natural language processing (NLP) is still on the starting stage. In this paper, we proposed a scheme that emotion recognition from text through classification with the rough set theory and the support vector machines (SVMs). The basic steps are firstly to sample data sets, to build the decisions table, and to find importance of attributions and the simplest form of decisions table according to relative reduction and then the rough set model of system is obtained, finally train the predicting model by the SVMs. Our experiment results show that rough set theory and SVMs method are effective in emotion recognition, and the high recognition rate is resulted.