A Method of Text Sentiment Classification Based on Weighted Rough Membership

Facing with promptly increasing reviews on the Web, it has been great challenge for information science and technology that how people effectively organize and process document data hiding large amounts of information to meet with particular needs. Text sentiment classification aims at developing some new theories and methods to automatically explore the sentiment orientation of a text by mining and analyzing subjective information in texts such as standpoint, view, attitude, mood, and so on. A method of text sentiment classification based on weighted rough membership is proposed in this paper. In the method, the model of text expression is established based on two-tuples attribute (feature, feature orientation intensity), by introducing feature orientation intensity into the method of vector space representation. An attribute discretization method is proposed based on the sentiment orientation sequence for feature selection unifying the discretization processing to depress data dimension. To utilize the feature orientation intensity, a weighted rough membership is defined for classifying new sentiment text. Compared with SVM classifier, on the reality car review corpus, the proposed method based on rough membership for text sentiment classification has the best performance after data being compressed in a certainty extent for text sentiment classification.