Browser

Clustering Suggestion for Chinese News Web Pages From Multi-Media Sources

Free registration required

Executive Summary

There exists some news obviously classified into incorrect categories on Chinese web pages portal. The main reasons could be that it is difficult to automatically classify Chinese news and the news appearing on web pages portal are retrieved from many media sources. In this paper, the authors integrate genetic algorithm and multi-class Support Vector Machine (SVM) classifier to construct a Chinese news classification method. In addition, they find that some similar documents are scattered in different categories.

  • Format: PDF
  • Size: 134.6 KB