Polarity text filtering based on semantic analysis

Yunfa Hu

Journal of China Institute of Communications · 2004 · 11 citations · 0 references

Concepts

Abstract

Text filtering technology based on statistics usually is ineffective when it deals with polarity text. The method overlooks the semantic restriction of text, so it isnt good for identifying polarity information. The paper provides a new text filtering method based on semantic analysis, which takes into account semantic relations in text. The experiment results indicate that the method efficiently recognizes and heads off the polarity information.