Research on Document Content Classification on Mathematical Regression Model

摘要

To improve the document classification problem, this study proposes a classification algorithm based on mathematical regression model, making Chinese document classification get rid of the dependence on traditional dictionary method. The method of extracting high frequency keywords, establishes the appropriate matrix model, making a high-dimensional document change into a low-dimensional document, and then use mathematical regression model to give a comprehensive feature weighting function by corpus training. It explored an approach to avoid the traditional method of the problem of curse of dimensionality.