A Study of Chinese News Headline Classification Based on Keyword Feature Expansion

Abstract Existing work generally classifies news headlines as a matter of short text classification. However, due to the strong domain nature and limited length headlines, their classification results are usually determined by several specific keywords, which makes traditional method ineffective. In this paper, we propose new identify keywords in expand features from sentence level word respectively, finally use convolutional neural networks (CNN) extract classify features. The proposed model was tested on Sogou News Corpus dataset achieved 93.42 $$\%$$ % accuracy.